Hands-On Activity: Create a custom data

table
Activity Overview
In this activity, you will use a spreadsheet to build a custom data table and analyze your data
with functions. To begin, suppose you're a data analyst working for a recruiting agency. This
recruiting agency helps all sorts of companies find skilled people to fill open data analytics
jobs. The agency has collected data about job applications for opportunities posted on its
website over the course of a year.

Scenario
Review the following scenario. Then complete the step-by-step instructions.

The agency has asked your team to optimize its online application process. Your assignment
is to summarize the agency’s job application data. In particular, you want to answer the
following questions:

 What was the total number of applications received each month?

 How many applications were received?
 In which months were the lowest and highest number of applications received?
 What was the average number of applications received per month?

To do this, you’ll work with a spreadsheet. You’ll use spreadsheet functions to make
calculations based on your data and create a custom data table to summarize your results.

By the time you complete this activity, you will be able to import a spreadsheet file, sort data,
create a custom data table, and use spreadsheet functions to work with your data.
Spreadsheets are an essential tool for every data analyst. Using spreadsheets to organize and
analyze data is an important skill that you will continue to develop throughout your career.

Step-By-Step Instructions
Follow the instructions to complete each step of the activity. Then answer the questions at the
end of the activity before going to the next course item.
Step 1: Access the spreadsheet
To use the spreadsheet for this course item, select the link below, then select the “Use
Template” button to open your own version of the spreadsheet.

Note: This dataset is large, so it may take a few seconds for the rows to appear.

Link to template: Untitled Spreadsheet

OR

Download the data:

 Untitled spreadsheet
XLSX File

Step 2: Understand the data

The agency’s data contains information about all of the data analytics job applications
received. The data includes the following column headers: Applicant ID, Date, Job Title,
Job Location, Hired, and Easy Apply. Below is a description of each column header and
sample values.

Column
Column Description Sample Data
Name
Applicant
Unique identifier for the applicants 11578773
ID
Date The date and time each application was received 1/1/2023 0:01:00
PHARMACEUTICAL DA
Job Title The data analytics position applied for
ANALYST
Job Location Where the job is located Lima, Peru
Hired Indicates if an applicant was hired TRUE
TRUE if the application was submitted directly on the agency's website; FALSE if
Easy Apply TRUE
the application was downloaded and submitted via email
Step 3: Sort your data
Because you want to answer questions based on a specific timeframe (in this case,
applications received per month in 2023), start by sorting the data by date. Sorting involves
arranging data into a meaningful order to make it easier to understand, analyze, and visualize.
Considering the order in which each application was received can help you discover trends in
data analytics job applications.

1. First, rename your spreadsheet. Select Untitled Spreadsheet and enter a new name. Use
data_analyst_jobs_2023 or a similar name that clearly describes the data your spreadsheet
contains.
2. When you are working in a spreadsheet, you can have multiple sheets open. Currently,
your spreadsheet contains one sheet labeled 2023_data_analyst_job. Rename this sheet by
selecting the sheet tab and choosing Rename from the menu. Then, enter raw data.
3. Make the columns Job Title (C) and Job Location (D) wider by dragging the right
boundary of the column headings.

4. Select all the data in the spreadsheet by selecting the cell where the rows and columns
intersect.

5. From the menu bar, select Data > Sort range > Advanced range sorting options.

6. In the pop-up window, select the Data has header row box.

7. In the Sort by dropdown, choose the header Date. Then, select A to Z to sort in ascending
order.

8. Finally, select Sort.

Your spreadsheet now displays job applications received in chronological order.

Step 4: Create a custom data table

Now that you’ve sorted your data, you’re ready to create a custom data table to help you
answer each of your questions. Your table will clearly summarize the data. Plus, if you want
to share your results, your table will be well-organized and easy to understand.

Count the number of applications received each month

First, use spreadsheet functions to help you find the total number of applications received in
each month.
1. To start, select the Add sheet icon (the plus sign) in the menu bar to add a new sheet to
your spreadsheet. You’ll create your data table in this sheet

2. Rename the new sheet. Select the sheet tab and choose Rename on the menu. Then, enter
summary data.

3. Next, add column headers to your table. In cell A1 of your summary data sheet, enter
Month. In cell B1, enter Applications.

4. Underneath the Month label in cell A2, enter January. Press Enter.

5. Now, use autofill to add the rest of the months of the year. Select cell A2 again. The fill
handle will appear in the cell. Select on the fill handle and drag it down to cell A13 to autofill
all the months of the year.

6. Next, convert the number values in the Date column in the raw data sheet into text. Select
the raw data tab to return to the raw data sheet. In cell G1, enter Month.

7. The TEXT function converts a number into text according to a specified format. In this
case, list them in which an application was received. Use the format “mmmm” for the full
name of the month. In cell G2, enter the following code (do not copy+paste):

=TEXT(B2,"mmmm")

The first entry B2 refers to the cell you want to convert. The second entry ("mmmm") refers
to the specific format you want to use. Press Enter.

(Note: It is very important that you manually enter all formulas and functions. They should
not be copied and pasted from the activity, as this will result in an error message.)

8. If a box pops up with the option to autofill the column, select the check mark or enter Ctrl
+ Enter (Windows) or Cmd + Return (Mac). If this box does not pop up, select cell G2.
Then, double-click on the fill handle to copy the function down the column. This will
populate all the cells in the column with the corresponding month.

9. Now you're ready to total the applications by month. You could do this manually, by
filtering the data and counting the number of entries for each month, but this would take a
long time and be prone to errors. Instead, use the COUNTIF function.

10. The COUNTIF function quickly counts how many items in a range of cells meet a given
criterion. First, select the summary data tab to return to your summary data sheet. Then, in
cell B2, enter =COUNTIF('raw data'!G:G,A2). The first entry 'raw data'!G:G refers to the
range where you are counting the data. The range is located on your raw data sheet 'raw
data'! and includes all column G G:G entries. This column contains the data for months. The
second entry A2 refers to the criterion you want to count. In this case, it’s “January,” the
value in cell A2 of your summary data sheet. The function calculates how many times
January (the criterion) appears in the Month column (the range).

11. Press Enter. You’ll notice the value 2387 appears in cell B2. This means that 2,387 job
applications were submitted in January.
 12. Select cell B2. Double-click the fill handle to copy the function down through cell B13.

Now your table lists the total number of applications submitted for each month:

Month Applications
January 2387
February 2312
March 2536
April 2544
May 2954
June 2990
July 3138
August 2969
September 2865
October 2751
November 2508
December 2642
Step 5: Find the total number of applications received
Now that you’ve calculated the number of applications received in each month, use
spreadsheet formulas to calculate the total number of applications received.

1. Label the cell in which you’ll calculate your result. In cell A14, enter Total.
2. In cell B14, enter =SUM(B2:B13). This function calculates the number of applications
received from January through December.
3. Cell B14 contains the total number of applications, 32596.
Step 6: Find the months with the lowest and highest number
of applications received
Use the MIN and MAX functions to calculate this information.

1. First, make labels for your results. In cell A16, enter Min. In cell A17, enter Max.
2. The MIN function returns the minimum value in a numeric range. In cell B16, enter
=MIN(B2:B13). The result, 2312, is the lowest number of applications received in any
month in 2023.
3. The MAX function returns the maximum value in a numeric dataset. In cell B17, enter
=MAX(B2:B13). The result, 3138, is the highest number of applications received in any
month in 2023.
Step 7: Find the average number of applications received per
month
Use the AVERAGE function to calculate this information.

1. First, make labels for your results. In cell A18, enter Avg.
2. The AVERAGE function returns the average value in a numeric dataset. In cell B18, enter
=AVERAGE(B2:B13). The result, 2716.33, is the average number of monthly applications
received in 2023.
Your work will help your team discover important trends and patterns in the agency’s data
and generate insights for optimizing the application process. For example, because your
findings reveal that February was the slowest month, the agency can devote more of its
advertising and outreach budget to February and less to the peak month of July. This is the
strategic impact of data analysis.
Optional Step 8: Explore formatting options
Feel free to explore formatting options for your data table using bold, center align, fill color,
borders, and more. Formatting lets you highlight important information and helps capture the
attention of your audience.
Pro Tip: Save the activity template
Be sure to save a copy of the template you used to complete this activity. You can use it for
further practice or to help you work through your thought processes for similar tasks in a
future data analyst role.

Before solving a problem, understand it

Save note
TranscriptNotesDownloadsDiscuss
Interactive Transcript - Enable basic transcript mode by
pressing the escape key
You may navigate through the transcript using tab. To save a note for a section of text press CTRL + S. To
expand your selection you may use CTRL + arrow key. You may contract your selection using shift +
CTRL + arrow key. For screen readers that are incompatible with using arrow keys for shortcuts, you can
replace them with the H J K L keys. Some screen readers may require using CTRL in conjunction with the
alt key
Albert Einstein once said," If I were given one hour to save the planet, I would spend 59 minutes defining
the problem and one minute resolving it." Now, that might seem extreme, but it does show us just how
important it is to define the problems before trying to solve them. A lot of times, teams jump right into data
analysis before realizing a few months later that they are either solving the wrong problem or they don't
have the right data. In this video, we will learn how to develop a structured approach to defining the
problem domain. This is important because if you define the problem clearly from the start, it'll be easier to
solve, which saves a lot of time, money, and resources. In the data world, we call this first piece the
problem domain: the specific area of analysis that encompasses every activity affecting or affected by the
problem. Before we can do anything else, we need to understand the problem domain and all of its parts
and relationships so that we can discover the whole story. Actually calling it the first piece makes me think
of a jigsaw puzzle. Say you have a puzzle. Let's think of that puzzle as our problem domain. You have all
500 pieces but you lost the box. So you don't know what image the puzzle will reveal. Will it be an
animal? A waterfall? A bowl of oranges? Whatever it is, it's going to be tough trying to put it together
without an image you can refer to. Even the greatest puzzler in the galaxy would need a new process and
lots of time to complete that puzzle. Data analysts face the same kinds of challenges too. You might
remember that data analysts aren't always given the complete picture at the start of a project. A big part of
their job is to develop a structured approach and use critical thinking to find the best solution. That starts
with understanding the problem domain. This is where structured thinking comes into play. To
successfully solve a problem as a data analyst, you need to train your brain to think structurally. That's
exactly what you'll learn coming up. See you there.
Earlier I told you that carefully defining a business problem can ultimately save time, money, and
resources. All of this is achieved through structured thinking. Structured thinking is the process of
recognizing the current problem or situation, organizing available information, revealing gaps and
opportunities, and identifying the options. In other words, it's a way of being super prepared. It's having a
clear list of what you are expected to deliver, a timeline for major tasks and activities, and checkpoints so
the team knows you're making progress. In this video, we'll look at how structured thinking helps us save
time and effort, but also makes our job as data analysts easier because it allows us to better understand the
work we are doing. In the business world, it's common for teams to spend hours of valuable time trying to
solve an important problem, only to end up back where they started. Not only is the initial problem not
resolved, but they've spent hours not resolving it. This outcome negatively affects you, your team, and the
organization as a whole. But it can usually be prevented. Many times the situation is a result of not fully
understanding the issue. Structured thinking will help you understand problems at a high level so that you
can identify areas that need deeper investigation and understanding. The starting place for structured
thinking is the problem domain, which you might have remembered from earlier. Once you know the
specific area of analysis, you can set your base and lay out all your requirements and hypotheses before
you start investigating. With a solid base in place, you'll be ready to deal with any obstacles that come up.
What kind of obstacles? Well, let's say you're asked to predict the future value of an apartment building
based on a given dataset. You have hundreds of variables and every one is crucial to your analysis. But
what if one variable accidentally gets left out, like square footage, for example? You'd have to go back and
redo all your hard work. That's because missing variables can lead to inaccurate conclusions. Another way
that you can practice structured thinking and avoid mistakes is by using a scope of work. A scope of work
or SOW is an agreed-upon outline of the work you're going to perform on a project. For many businesses,
this includes things like work details, schedules, and reports that the client can expect. Now, as a data
analyst, your scope of work will be a bit more technical and include those basic items we just mentioned,
but you'll also focus on things like data preparation, validation, analysis of quantitative and qualitative
datasets, initial results, and maybe even some visuals to really get the point across. Let's bring a scope of
work to life with a simple example. Say a couple has hired a wedding planner. We'll focus on just one task,
the wedding invitations. Here's what might be in scope of work: deliverables, timeline, milestones, and
reports. Let's break down just one of these, deliverables. The wedding planner and couple will need to
decide on the invitation, make a list of people to invite, collect their addresses, print the invitations, address
the envelopes, stamp them, and mail them out. Now let's check out the timelines. You'll notice the dates
and the milestones which keep us on track. Finally, we have the reports, which give our couple some peace
of mind by telling them when each step is complete. A scope of work can be a simple but powerful tool.
With a solid scope of work, you'll be able to address any confusion, contradictions, or questions about the
data up-front and make sure these sneaky setbacks don't stand in your way. This is a simple example of
what a scope of work might look like. But later, you'll be able to practice building your own. Next up in
our scope, we'll check out setbacks from a different angle by learning the importance of contextualizing
data and avoiding bias. Looking forward to sharing some cool insights with you.

Welcome back. In this video, we'll explore the importance of contextualizing data, and recognizing data
bias. Let's get started. Data doesn't live in a vacuum, it needs context. Earlier, we learnt that context is the
condition in which something exists or happens. Actions can be appropriate in some context, but
inappropriate in others, for example, yelling move, is rude one context, if your friend is standing in front of
the TV, but it's entirely appropriate in another, if that friend is about to get hit by a kid on a tricycle. Do
you see the difference? In the world of data, numbers don't mean much without context. I'll let my fellow
Googler Ed, tell you a little bit more about that. As we have more and more data available to us. We can
leverage that data in increasingly sophisticated ways, and generate more powerful insights from it. We use
data at many different levels. Sometimes our data is descriptive, answering questions like, how much did
we spend on travel last month? Data becomes more valuable, as we generate diagnostic and predictive
insights, like understanding why travel spend increased last month. Data is most valuable, however, when
we can generate prescriptive insights. For example, how can we leverage data to incentivize more efficient
travel? Figuring out what data means, is just as important as collecting it. As a data analyst, a big part of
your job, is putting data into context. It's also up to you, to remain objective and recognize all sides of an
argument, before drawing conclusions. The thing about context, is that it's very personal. If two people
curate the same data set, and follow the same directions, there's a chance they will end up with different
results. Why? Because there is no universal set of contextual interpretations. Everyone approaches it in
their own way. Even if the data collection process is correct, the analysis can still be misinterpreted.
Conclusions can be influenced by your own conscious and subconscious biases, which are based on
cultural, social and market norms. For example, if you ask a Boston resident, which baseball team is the
best, chances are, they're going to say Boston Red Sox. Which brings us to a major limitation of data
analytics. If the analysis is not objective, the conclusions can be misleading. To really understand what the
data is about, you have to think through who, what, where, when, how and why. It's good to ask yourself
questions like, who collected the data? And what is it about? What does the data represent in the world,
and how does it relate to other data? When, was the data collected? Data collected awhile ago may have
certain limitations, given the present day situation. For example, if we collected phone numbers over the
past century, at some point, mobile phones would have been introduced, leading to the need for an
additional phone number field. You should also think about, where, was the data collected? A lot can
change across cities, states and countries, and how was it collected. A survey might not be as effective as
an in-person interview, for example. Of course, there's the, why. The why can have a particularly strong
relationship with bias. Why? Because sometimes, data is collected, or even made up, to serve an agenda.
The best thing you can do for the fairness and accuracy of your data, is to make sure you start with an
accurate representation of the population, and collect the data in the most appropriate, and objective way.
Then, you'll have the facts so you can pass on to your team. Hopefully you now understand the importance
of fair and objective data, and how important a context is, when it comes to understanding and interpreting
it. Next up, we'll figure out how we can bring it to life.

The importance of context

Context in data analytics is the condition and circumstances that surround and give meaning
to the data. Context is important in data analytics because it helps make disorganized data
accessible and understood. The fact is, data has little value if it is not paired with context.
Understanding the context behind the data can help us make it more meaningful at every
stage of the data analysis process. For example, you might be able to make a few guesses
about what you're looking at in the following table, but you couldn't be certain without more
context.

2010 28000
2005 18000
2000 23000
1995 10000
On the other hand, if the first column was labeled to represent the years when a survey was
conducted, and the second column showed the number of people who responded to that
survey, then the table would start to make a lot more sense. Take this a step further, and you
might notice that the survey is conducted every 5 years. This added context helps you
understand why there are five-year gaps in the table.

Years (Collected every 5 years) Respondents

2010 28000
2005 18000
2000 23000
1995 10000
Context can turn raw data into meaningful information. It is very important for data
analysts to contextualize their data. This means giving the data perspective by defining it. To
do this, you need to identify:

 Who: The person or organization that created, collected, and/or funded the data
collection
 What: The things in the world that data could have an impact on
 Where: The origin of the data
 When: The time when the data was created or collected
 Why: The motivation behind the creation or collection
 How: The method used to create or collect it
Understanding and including the context is important during each step of your analysis
process, so it is a good idea to get comfortable with it early in your career. For example,
when you collect data, you’ll also want to ask questions about the context to make sure that
you understand the business and business process. During organization, the context is
important for your naming conventions, how you choose to show relationships between
variables, and what you choose to keep or leave out. And finally, when you present, it is
important to include contextual information so that your stakeholders understand your
analysis.

Skip to main content

SEARCH IN COURSE
Search
English
 1
 Menu pop-up Collapsed

1.

2. Module 3

3. Self-Reflection: Work with datasets

PreviousNext

Self-Reflection: Work with datasets

Submit your assignment
Resume assignment
Receive grade
To Pass100% or higher
Your grade
-Not available
Like
Dislike
Report an issue














Ctrl+M
Back

Self-Reflection: Work with datasets

Practice Quiz. • 20 min. • 1 total point available.1 total point
English
DueJun 28, 11:59 PM IST
Activity overview
Recently, you have explored formulas and functions in spreadsheets, created custom data
tables, and explored how to save time with structured thinking. Now, you’ll work with and
manipulate datasets, then respond to brief questions.

These things will help you to develop insights into your own learning journey and prepare
you to apply your knowledge of analytics, crafting SMART questions, and developing a
scope of work (SOW). As you answer questions—and come up with questions of your own—
consider the concepts, practices, and principles that have helped refine your understanding
and reinforce your learning. You’ve done the hard work, so make sure to get the most out of
it by practicing what you’ve learned!
Step-By-Step Instructions
Follow the instructions to complete each step of the activity. Then answer the question at the
end of the activity before going to the next course item.
Step 1: Access the template
To use the template for this course item, click the link below and select “Use Template.”

Link to template: Data Analysis Project Scope-of-Work (SOW) Template

 OR

If you don’t have a Google account, download the template directly from the attachment
below.

Scope-Of-Work Template
DOCX File

Step 2: Examine a dataset on Kaggle

Kaggle is a data science platform that houses a variety of datasets. You will need to create a
free account to begin exploring and analyzing different datasets. Then, this activity will
provide an example of how to use a dataset to formulate SMART questions, create an SOW,
and perform analytics in a spreadsheet. After that, you’ll have an opportunity to explore a
dataset of your choice to formulate your own SMART questions, create your own SOW, and
perform analytics in a spreadsheet that you can add to your professional portfolio.

1. Download Lettuce Growth Days from the Kaggle website. After you extract the files, open
the lettuce_dataset CSV file in Google Sheets or Excel.
2. Analyze the dataset’s column names, values, and summary statistics (mean, median,
quartiles, and min/max values), as well as contemplate goals to formulate SMART
questions. SMART questions for the Lettuce Growth Days data could include:
a. Specific: Is there a connection between humidity and temperature?
b. Measurable: How much growth is normal or expected over a one-week period?
c. Action-oriented: If total dissolved solids are increased when growing lettuce, will
it shorten the time needed for the plants to reach maturity?
d. Relevant: Based on the dataset, how can predictions about growth be made given
the conditions?
e. Time-bound: What is the date range for this dataset? Do we need an understanding
of this data for next season?
3. Based on the SMART questions, create an SOW that outlines the analytics tasks. An
example of an SOW for Lettuce Growth Days can be found in the Lettuce dataframe:
Example SOW.
4. Perform basic analytics on the dataset. For the Lettuce Growth Days dataset, analytics
could include:
a. Converting Celsius to Farenheit
b. Converting days to weeks
c. Modifying the humidity column
d. Creating a new spreadsheet to perform exploratory data analysis
 Step 3: Explore more datasets
1. From the Kaggle homepage, select Datasets to view the available datasets.
2. Select a category that interests you or that aligns with your career goals. Select Download
to download the data and begin analyzing it. Based on the dataset you chose, create a list of
3-5 SMART questions, develop a completed SOW, and create a new Google Sheet with
performed analytics that best align to your dataset. Note: It’s important to check the
Kaggle Usability Score when choosing a dataset on Kaggle; the higher the score, the easier
the data will be to work with. Find the Usability Score in the dataset information. It ranks
the dataset’s completeness, credibility, and compatibility.
3. Share your findings, SOW, and analytics on a discussion board in the discussion forums.
Pro Tip: Save the blank activity template
1.
Question 1
Reflection
Consider what you’ve learned about working with datasets to formulate SMART questions, crafting an
SOW, and performing data analytics in this reflection:

 Why is it important to create SMART questions about your datasets? How do these questions benefit
your work as a data professional?
 Why is it important to determine your SMART questions and answers before crafting an SOW?
 Why is it important to perform data analysis on datasets?
Now, write 2-3 sentences (40-60 words) in response to each of these questions. Enter your response in the
text box below.
1 point

Skip to main content

 SEARCH IN COURSE
Search
English
 1
 Menu pop-up Collapsed

1.

2. Module 3

3. Test your knowledge on structured thinking

PreviousNext

Test your knowledge on structured thinking

Review Learning Objectives
Submit your assignment
Resume assignment
Receive grade
To Pass75% or higher
Your grade
-Not available
Like
Dislike
Report an issue














Ctrl+M
Back
Test your knowledge on structured thinking
Practice Quiz. • 8 min. • 4 total points available.4 total points
English
DueJun 28, 11:59 PM IST
1.
Question 1
What is the term for the specific area of analysis that encompasses every activity affecting or affected by a
problem?
1 point
Problem domain
Problem context
Problem structure
Problem scope

2.
Question 2
What are the key elements of structured thinking? Select all that apply.
1 point
Implement a solution
Organize available information
Recognize the current problem or situation
Reveal gaps and opportunities

3.
Question 3
Fill in the blank: A scope of work is an agreed-upon _____ of the work you’re going to perform on a
project.
1 point
to-do list
diagram
report
outline

4.
Question 4
What are some strategies data professionals use to help ensure they work with data that is accurate and
fair? Select all that apply.
1 point
Ensure an accurate representation of the population in a sample
Collect data in an impartial manner
Maintain objectivity by not asking where the data originated
Consider different viewpoints before drawing conclusions

MODULE 4
As a data analyst, you'll be required to focus on a lot of different things, And your stakeholders'
expectations are one of the most important. We're going to talk about why stakeholder expectations are so
important to your work and look at some examples of stakeholder needs on a project. By now you've heard
me use the term stakeholder a lot. So let's refresh ourselves on what a stakeholder is. Stakeholders are
people that have invested time, interest, and resources into the projects that you'll be working on as a data
analyst. In other words, they hold stakes in what you're doing. There's a good chance they'll need the work
you do to perform their own needs. That's why it's so important to make sure your work lines up with their
needs and why you need to communicate effectively with all of the stakeholders across your team. Your
stakeholders will want to discuss things like the project objective, what you need to reach that goal, and
any challenges or concerns you have. This is a good thing. These conversations help build trust and
confidence in your work. Here's an example of a project with multiple team members. Let's explore what
they might need from you at different levels to reach the project's goal. Imagine you're a data analyst
working with a company's human resources department. The company has experienced an increase in its
turnover rate, which is the rate at which employees leave a company. The company's HR department wants
to know why that is and they want you to help them figure out potential solutions. The Vice President of
HR at this company is interested in identifying any shared patterns across employees who quit and seeing
if there's a connection to employee productivity and engagement. As a data analyst, it's your job to focus
on the HR department's question and help find them an answer. But the VP might be too busy to manage
day-to-day tasks or might not be your direct contact. For this task, you'll be updating the project manager
more regularly. Project managers are in charge of planning and executing a project. Part of the project
manager's job is keeping the project on track and overseeing the progress of the entire team. In most cases,
you'll need to give them regular updates, let them know what you need to succeed and tell them if you have
any problems along the way. You might also be working with other team members. For example, HR
administrators will need to know the metrics you're using so that they can design ways to effectively gather
employee data. You might even be working with other data analysts who are covering different aspects of
the data. It's so important that you know who the stakeholders and other team members are in a project so
that you can communicate with them effectively and give them what they need to move forward in their
own roles on the project. You're all working together to give the company vital insights into this problem.
Back to our example. By analyzing company data, you see a decrease in employee engagement and
performance after their first 13 months at the company, which could mean that employees started feeling
demotivated or disconnected from their work and then often quit a few months later. Another analyst who
focuses on hiring data also shares that the company had a large increase in hiring around 18 months ago.
You communicate this information with all your team members and stakeholders and they provide
feedback on how to share this information with your VP. In the end, your VP decides to implement an in-
depth manager check-in with employees who are about to hit their 12 month mark at the firm to identify
career growth opportunities, which reduces the employee turnover starting at the 13 month mark. This is
just one example of how you might balance needs and expectations across your team. You'll find that in
pretty much every project you work on as a data analyst, different people on your team, from the VP of HR
to your fellow data analysts, will need all your focus and communication to carry the project to success.
Focusing on stakeholder expectations will help you understand the goal of a project, communicate more
effectively across your team, and build trust in your work. Coming up, we'll discuss how to figure out
where you fit on your team and how you can help move a project forward with focus and determination.

Balance needs and expectations across your team

Interactive Transcript - Enable basic transcript mode by pressing the escape key
You may navigate through the transcript using tab. To save a note for a section of text press CTRL + S. To
expand your selection you may use CTRL + arrow key. You may contract your selection using shift +
CTRL + arrow key. For screen readers that are incompatible with using arrow keys for shortcuts, you can
replace them with the H J K L keys. Some screen readers may require using CTRL in conjunction with the
alt key.

So now that we know the importance of finding the balance across your stakeholders and your team
members, I want to talk about the importance of staying focused on the objective. This can be tricky when
you find yourself working with a lot of people with competing needs and opinions. However, by asking
yourself a few simple questions at the beginning of each task, you can ensure that you're able to stay
focused on your objective while still balancing stakeholder needs.

Let's think about our employee turnover example from the last video. There, we were dealing with many
different team members and stakeholders like managers, administrators, and even other analysts. As a data
analyst, you'll find that balancing everyone's needs can be a little chaotic sometimes. Part of your job is to
look past the clutter and stay focused on the objective. It's important to concentrate on what matters and
not get distracted.

As a data analyst, you could be working on multiple projects with lots of different people. However, no
matter what project you're working on, there are three things you can focus on that will help you stay on
task. First, who are the primary and secondary stakeholders? Second, who is managing the data? And third,
where can you go for help? Let's see if we can apply those questions to our example project.

The first question you can ask is about who those stakeholders are. The primary stakeholder of this project
is probably the Vice President of HR, who hopes to use the project's findings to make new decisions about
company policy. You'd also be giving updates to your project manager, team members, or other data
analysts who are depending on your work for their tasks. These are your secondary stakeholders. Take
time at the beginning of every project to identify your stakeholders and their goals. Then see who else is on
your team and what their roles are.

Next, you'll want to ask who's managing the data. For example, think about working with other analysts on
this project. You're all data analysts, but you may manage different data within your project. In our
example, another data analyst was focused on managing the company's hiring data. Their insights around a
surge of new hires 18 months ago turned out to be a key part of your analysis. If you hadn't communicated
with this person, you might have spent a lot of time trying to collect or analyze hiring data yourself or you
may not have even been able to include it in your analysis at all. Instead, you were able to communicate
your objectives with another data analyst and use existing work to make your analysis richer. By
understanding who's managing the data, you can spend your time more productively.

Next, you need to know where you can go when you need help. This is something you should know at the
beginning of any project you work on. If you run into bumps in the road on your way to completing a task,
you need someone who is best positioned to take down those barriers for you. When you know who's able
to help, you'll spend less time worrying about other aspects of the project and more time focused on the
objective. So who could you go to if you ran into a problem on this project?

Project managers support you and your work by managing the project timeline, providing guidance and
resources, and setting up efficient workflows. They have a big picture view of the project because they
know what you and the rest of the team are doing. This makes them a great resource if you run into a
problem. In the employee turnover example, you would need to be able to access employee departure
survey data to include in your analysis. If you're having trouble getting approvals for that access, you can
speak with your project manager to remove those barriers for you so that you can move forward with your
project.

Your team depends on you to stay focused on your task so that, as a team, you can find solutions. By
asking yourself three easy questions at the beginning of new projects, you'll be able to address stakeholder
needs, feel confident about who is managing the data, and get help when you need it so that you can keep
your eyes on the prize: the project objective.

So far, we've covered the importance of working effectively on a team while maintaining your focus on
stakeholder needs. Coming up, we'll go over some practical ways to become better communicators so that
we can help make sure the team reaches its goals.

Welcome back. We've talked a lot about understanding your stakeholders and your team so that you can
balance their needs and maintain a clear focus on your project objectives. A big part of that is building
good relationships with the people you're working with. How do you do that? Two words: clear
communication.

Now we're going to learn about the importance of clear communication with your stakeholders and team
members. Start thinking about who you want to communicate with and when. First, it might help to think
about communication challenges you might already experience in your daily life. Have you ever been in
the middle of telling a really funny joke only to find out your friend already knows the punchline? Or
maybe they just didn't get what was funny about it? This happens all the time, especially if you don't know
your audience.

This kind of thing can happen at the workplace too. Here's the secret to effective communication: Before
you put together a presentation, send an email, or even tell that hilarious joke to your co-worker, think
about who your audience is, what they already know, what they need to know, and how you can
communicate that effectively to them. When you start by thinking about your audience, they'll know it and
appreciate the time you took to consider them and their needs.

Let's say you're working on a big project, analyzing annual sales data, and you discover that all of the
online sales data is missing. This could affect your whole team and significantly delay the project. By
thinking through these four questions, you can map out the best way to communicate across your team
about this problem.

First, you'll need to think about who your audience is. In this case, you'll want to connect with other data
analysts working on the project, as well as your project manager and eventually the VP of sales, who is
your stakeholder. Next, you'll think through what this group already knows. The other data analysts
working on this project know all the details about which dataset you are using already, and your project
manager knows the timeline you're working towards. Finally, the VP of sales knows the high-level goals of
the project.

Then you'll ask yourself what they need to know to move forward. Your fellow data analysts need to know
the details of where you have tried so far and any potential solutions you've come up with. Your project
manager would need to know the different teams that could be affected and the implications for the project,
especially if this problem changes the timeline. Finally, the VP of sales will need to know that there is a
potential issue that would delay or affect the project.

Now that you've decided who needs to know what, you can choose the best way to communicate with
them. Instead of a long, worried email which could lead to lots of back and forth, you decide to quickly
book a meeting with your project manager and fellow analysts. In the meeting, you let the team know
about the missing online sales data and give them more background info. Together, you discuss how this
impacts other parts of the project. As a team, you come up with a plan and update the project timeline if
needed. In this case, the VP of sales didn't need to be invited to your meeting, but would appreciate an
email update if there were changes to the timeline, which your project manager might send along herself.

When you communicate thoughtfully and think about your audience first, you'll build better relationships
and trust with your team members and stakeholders. That's important because those relationships are key
to the project's success and your own too. When you're getting ready to send an email, organize a meeting,
or put together a presentation, think about who your audience is, what they already know, what they need
to know, and how you can communicate that effectively to them.

Next up, we'll talk more about communicating at work, and you'll learn some useful tips to make sure you
get your message across clearly.

No matter where you work, you'll probably need to communicate with other people as part of your day-to-
day. Every organization and every team in that organization will have different expectations for
communication. Coming up, we'll learn some practical ways to help you adapt to those different
expectations and some things that you can carry over from team to team. Let's get started.

When you start a new job or a new project, you might find yourself feeling a little out of sync with the rest
of your team and how they communicate. That's totally normal. You'll figure things out in no time if you're
willing to learn as you go and ask questions when you aren't sure of something. For example, if you find
your team uses acronyms you aren't familiar with, don't be afraid to ask what they mean. When I first
started at Google, I had no idea what LGTM meant and I was always seeing it in comment threads. Well, I
learned it stands for "looks good to me" and I use it all the time now if I need to give someone my quick
feedback. That was one of the many acronyms I've learned, and I come across new ones all the time and
I'm never afraid to ask.

Every work setting has some form of etiquette. Maybe your team members appreciate eye contact and a
firm handshake, or it might be more polite to bow, especially if you find yourself working with
international clients. You might also discover some specific etiquette rules just by watching your
coworkers communicate. And it won't just be in-person communication you'll deal with. Almost 300
billion emails are sent and received every day, and that number is only growing. Fortunately, there are
useful skills you can learn from those digital communications too.

You'll want your emails to be just as professional as your in-person communications. Here are some things
that can help you do that. Good writing practices will go a long way to make your emails professional and
easy to understand. Emails are naturally more formal than texts, but that doesn't mean that you have to
write the next great novel. Just taking the time to write complete sentences that have proper spelling and
punctuation will make it clear you took time and consideration in your writing. Emails often get forwarded
to other people to read, so write clearly enough that anyone could understand you. I like to read important
emails out loud before I hit send; that way, I can hear if they make sense and catch any typos.

Keep in mind the tone of your emails can change over time. If you find that your team is fairly casual,
that's great. Once you get to know them better, you can start being more casual too, but being professional
is always a good place to start. A good rule of thumb: Would you be proud of what you had written if it
were published on the front page of a newspaper? If not, revise it until you are. You also don't want your
emails to be too long. Think about what your team member needs to know and get to the point instead of
overwhelming them with a wall of text. You'll want to make sure that your emails are clear and concise so
they don't get lost in the shuffle.

Let's take a quick look at two emails so that you can see what I mean. Here's the first email. There's so
much written here that it's kind of hard to see where the important information is. And this first paragraph
doesn't give me a quick summary of the important takeaways. It's pretty casual too; the greeting is just
"Hey," and there's no sign-off. Plus, I can already spot some typos. Now let's take a look at the second
email. Already, it's less overwhelming, right? Just a few sentences, telling me what I need to know. It's
clearly organized, and there's a polite greeting and sign-off. This is a good example of an email; short and
to the point, polite and well-written—all of the things we've been talking about so far.

But what do you do if what you need to say is too long for an email? Well, you might want to set up a
meeting instead. It's important to answer in a timely manner as well. You don't want to take so long
replying to emails that your coworkers start wondering if you're okay. I always try to answer emails in 24-
48 hours, even if it's just to give them a timeline for when I'll have the actual answers they're looking for.
That way, I can set expectations and they know I'm working on it.

That works the other way around too. If you need a response on something specific from one of your team
members, be clear about what you need and when you need it so that they can get back to you. I'll even
include a date in my subject line and bold dates in the body of my email, so it's really clear. Remember,
being clear about your needs is a big part of being a good communicator.

We covered some great ways to improve our professional communication skills, like asking questions,
practicing good writing habits, and some email tips and tricks. These will help you communicate clearly
and effectively with your team members on any project. It might take some time, but you'll find a
communication style that works for you and your team, both in person and online. As long as you're
willing to learn, you won't have any problems adapting to the different communication expectations you'll
see in future jobs.

Use multiple communication strategies to

reach your audience
Being able to communicate in multiple formats is a key skill for data analysts. Listening,
speaking, presenting, and writing skills will help you succeed in your projects and in your
career. This reading covers effective communication strategies, including examples of clearly
worded emails for common situations.

Here's an important first tip: Know your audience! When you communicate your analysis and
recommendations as a data analyst, it's vital to keep your audience in mind.

Be sure to answer these four important questions related to your audience:

1. Who is your audience?

2. What do they already know?
3. What do they need to know?
4. How can you best communicate what they need to know?
Project example
As a data analyst, you'll get plenty of requests and questions through email. Let’s walk
through an example of how you might approach answering one of these emails. Assume
you're a data analyst working at a company that develops mobile apps. Let's start by
reviewing answers to the four audience questions we just covered:

Kiri, Product Development Project Manager

Kiri received updates about our project from its planning stages, including the most recent
project report, sent two weeks ago.

Kiri needs an update on the analysis project’s progress and needs to know that the executive
team approved changes to the data and timeline. You know that adding a new variable to the
analysis will impact the current project timeline. Kiri will need to change the project’s
milestones and completion date.
You can start by sending an email update to Kiri with the latest timeline for the project, but a
meeting might be necessary if she wants to talk through her concerns about missing a
deadline.

Updated timeline email sample

After answering the audience questions, you have the key building blocks you need to write
an email to Kiri. Here's an example of how these questions can help organize the flow of the
email message:

Hello Kiri, (who is your audience?) Thank you for your email about the app analysis project's status. I
understand you're concerned about how adding this new data will impact the project timeline, and I'd be
glad to provide as much information about the project status as I can. (What do they already know? ) We
can include the new data that you've suggested however, we'll need time to collect and incorporate it into
our analysis. As a result, it will take an additional two weeks to include the new data, which changes our
analysis project timeline. (What do they need to know?) I plan to send out a full report on Monday. This
report will include the finalized timeline and share the latest findings, including any new insights we've
found. I understand you're waiting on our report, and I want to make sure that we're able to get you the
information you need. If you'd like to meet before the next report, please let me know what time would
work best for you. (How can you best communicate what they need to know?) Thank you, (your first
name)
After receiving your email, Kiri will have a clearer view of the changes to the analysis project
and will be able to make adjustments to work with the new timeline.

Project follow-up email sample

After the next report is completed, you can also send out a project update offering more
information. The email could look like this:
Hello Kiri, The app analysis report has been released, and I wanted to let you know that we are meeting all
deadlines in our new timeline. I've attached a copy of the report so that you can see the results. Analysis
with our new data has been included in the report, along with more details about the next steps. Please pass
this along to your team, and let me know if you need any more information. Thank you, [your first name]
Good communication keeps stakeholders updated on progress and ultimately helps prevent
problems. Carefully worded responses are key. Whether you gather and address feedback
using email, meetings, or reports, everyone you work with will know what to expect. As a
result, they will be able to better manage their own schedules, resources, and teams.

Working with stakeholders

Your data analysis project should answer the business task and create opportunities for data-driven
decision-making. That's why it is so important to focus on project stakeholders. As a data analyst, it is your
responsibility to understand and manage your stakeholders’ expectations while keeping the project goals
front and center.
You might remember that stakeholders are people who have invested time, interest, and resources into the
projects that you are working on. This can be a pretty broad group, and your project stakeholders may
change from project to project. But there are three common stakeholder groups that you might find
yourself working with: the executive team, the customer-facing team, and the data science team.

Let’s get to know more about the different stakeholders and their goals. Then we'll learn some tips for
communicating with them effectively.

Executive team
The executive team provides strategic and operational leadership to the company. They set goals, develop
strategy, and make sure that strategy is executed effectively. The executive team might include vice
presidents, the chief marketing officer, and senior-level professionals who help plan and direct the
company’s work. These stakeholders think about decisions at a very high level and they are looking for the
headline news about your project first. They are less interested in the details. Time is very limited with
them, so make the most of it by leading your presentations with the answers to their questions. You can
keep the more detailed information handy in your presentation appendix or your project documentation for
them to dig into when they have more time.

For example, you might find yourself working with the vice president of human resources on an analysis
project to understand the rate of employee absences. A marketing director might look to you for
competitive analyses. Part of your job will be balancing what information they will need to make informed
decisions with their busy schedule.

But you don’t have to tackle that by yourself. Your project manager will be overseeing the progress of the
entire team, and you will be giving them more regular updates than someone like the vice president of HR.
They are able to give you what you need to move forward on a project, including getting approvals from
the busy executive team. Working closely with your project manager can help you pinpoint the needs of
the executive stakeholders for your project, so don’t be afraid to ask them for guidance.
Customer-facing team
The customer-facing team includes anyone in an organization who has some level of interaction with
customers and potential customers. Typically they compile information, set expectations, and
communicate customer feedback to other parts of the internal organization. These stakeholders have their
own objectives and may come to you with specific asks. It is important to let the data tell the story and not
be swayed by asks from your stakeholders to find certain patterns that might not exist.

Let’s say a customer-facing team is working with you to build a new version of a company’s most popular
product. Part of your work might involve collecting and sharing data about consumers’ buying behavior to
help inform product features. Here, you want to be sure that your analysis and presentation focuses on
what is actually in the data-- not on what your stakeholders hope to find.

Data science team

Organizing data within a company takes teamwork. There's a good chance you'll find yourself working
with other data analysts, data scientists, and data engineers. For example, maybe you team up with a
company's data science team to work on boosting company engagement to lower rates of employee
turnover. In that case, you might look into the data on employee productivity, while another analyst looks
at hiring data. Then you share those findings with the data scientist on your team, who uses them to predict
how new processes could boost employee productivity and engagement. When you share what you found
in your individual analyses, you uncover the bigger story. A big part of your job will be collaborating with
other data team members to find new angles of the data to explore. Here's a view of how different roles on
a typical data science team support different functions:
Working effectively with stakeholders
When you're working with each group of stakeholders- from the executive team, to the customer-facing
team, to the data science team, you'll often have to go beyond the data. Use the following tips to
communicate clearly, establish trust, and deliver your findings across groups.

Discuss goals. Stakeholder requests are often tied to a bigger project or goal. When they ask you for
something, take the opportunity to learn more. Start a discussion. Ask about the kind of results the
stakeholder wants. Sometimes, a quick chat about goals can help set expectations and plan the next steps.

Feel empowered to say “no.” Let’s say you are approached by a marketing director who has a “high-
priority” project and needs data to back up their hypothesis. They ask you to produce the analysis and
charts for a presentation by tomorrow morning. Maybe you realize their hypothesis isn’t fully formed and
you have helpful ideas about a better way to approach the analysis. Or maybe you realize it will take more
time and effort to perform the analysis than estimated. Whatever the case may be, don’t be afraid to push
back when you need to.

Stakeholders don’t always realize the time and effort that goes into collecting and analyzing data. They
also might not know what they actually need. You can help stakeholders by asking about their goals and
determining whether you can deliver what they need. If you can’t, have the confidence to say “no,” and
provide a respectful explanation. If there’s an option that would be more helpful, point the stakeholder
toward those resources. If you find that you need to prioritize other projects first, discuss what you can
prioritize and when. When your stakeholders understand what needs to be done and what can be
accomplished in a given timeline, they will usually be comfortable resetting their expectations. You should
feel empowered to say no-- just remember to give context so others understand why.

Plan for the unexpected. Before you start a project, make a list of potential roadblocks. Then, when you
discuss project expectations and timelines with your stakeholders, give yourself some extra time for
problem-solving at each stage of the process.

Know your project. Keep track of your discussions about the project over email or reports, and be ready
to answer questions about how certain aspects are important for your organization. Get to know how your
project connects to the rest of the company and get involved in providing the most insight possible. If you
have a good understanding about why you are doing an analysis, it can help you connect your work with
other goals and be more effective at solving larger problems.

Start with words and visuals. It is common for data analysts and stakeholders to interpret things in
different ways while assuming the other is on the same page. This illusion of agreement* has been
historically identified as a cause of projects going back-and-forth a number of times before a direction is
finally nailed down. To help avoid this, start with a description and a quick visual of what you are trying to
convey. Stakeholders have many points of view and may prefer to absorb information in words or pictures.
Work with them to make changes and improvements from there. The faster everyone agrees, the faster you
can perform the first analysis to test the usefulness of the project, measure the feedback, learn from the
data, and implement changes.

Communicate often. Your stakeholders will want regular updates on your projects. Share notes about
project milestones, setbacks, and changes. Then use your notes to create a shareable report. Another great
resource to use is a change-log, which is a tool that will be explored further throughout the program. For
now, just know that a change-log is a file containing a chronologically ordered list of modifications made
to a project. Depending on the way you set it up, stakeholders can even pop in and view updates whenever
they want.

We discussed before how data has limitations. Sometimes you don't have access to the data you need, or
your data sources aren't aligned, or your data is unclean. This can definitely be a problem when you're
analyzing data, but it can also affect your communication with your stakeholders. That's why it's important
to balance your stakeholders' expectations with what is actually possible for a project. We're going to learn
about the importance of setting realistic, objective goals and how to best communicate with your
stakeholders about problems you might run into.

Keep in mind that a lot of things depend on your analysis. Maybe your team can't make a decision without
your report, or maybe your initial data work will determine how and where additional data will be
gathered. You might remember that we've talked about some situations where it's important to loop
stakeholders in, such as telling your project manager if you're on schedule or if you're having a problem.
Now, let's look at a real-life example where you need to communicate with stakeholders and what you
might do if you run into a problem.
Let's say you're working on a project for an insurance company. The company wants to identify common
causes of minor car accidents so that they can develop educational materials that encourage safer driving.
There are a few early questions you and your team need to answer: What driving habits will you include in
your dataset? How will you gather this data? How long will it take you to collect and clean that data before
you can use it in your analysis? Right away, you want to communicate clearly with your stakeholders to
answer these questions so you and your team can set a reasonable and realistic timeline for the project.

It can be tempting to tell your stakeholders that you'll have this done in no time, no problem. But setting
expectations for a realistic timeline will help you in the long run. Your stakeholders will know what to
expect when, and you won't be overworking yourself and missing deadlines because you overpromised. I
find that setting expectations early helps me spend my time more productively. So, as you're getting
started, you'll want to send a high-level schedule with different phases of the project and their approximate
start dates. In this case, you and your team establish that you'll need three weeks to complete the analysis
and provide recommendations, and you let your stakeholders know so they can plan accordingly.

Now, let's imagine you're further along in the project and you run into a problem. Maybe drivers have
opted into sharing data about their phone usage in the car, but you discover that some sources count GPS
usage and some don't in their data. This might add time to your data processing and cleaning and delay
some project milestones. You'll want to let your project manager know and maybe work out a new timeline
to present to stakeholders. The earlier you can flag these problems, the better. That way, your stakeholders
can make necessary changes as soon as possible.

Or what if your stakeholders want to add car model or age as possible variables? You'll have to
communicate with them about how that might change the model you've built, if it can be added before the
deadlines, and any other obstacles that they need to know so they can decide if it's worth changing at this
stage of the project. To help them, you might prepare a report on how their request changes the project
timeline or alters the model. You could also outline the pros and cons of that change.

You want to help your stakeholders achieve their goals, but it's important to set realistic expectations at
every stage of the project. This takes some balance. You've learned about balancing the needs of your team
members and stakeholders, but you also need to balance stakeholder expectations with what's possible with
the project's resources and limitations. That's why it's important to be realistic and objective and
communicate clearly. This will help stakeholders understand the timeline and have confidence in your
ability to achieve those goals.

So, we know communication is key and we have some good rules to follow for our professional
communication. Coming up, we'll talk even more about answering stakeholder questions, delivering data,
and communicating with your team.

Certainly! Here's the transcript arranged without changing the content:

---

I'm Sarah and I'm a senior analytical leader at Google. As a data analyst, there's going to be times where
you have different stakeholders who have no idea about the amount of time that it takes you to do each
project, and in the very beginning when I'm asked to do a project or to look into something, I always try to
give a little bit of expectation settings on the turn around because most of your stakeholders don't really
understand what you do with data and how you get it and how you clean it and put together the story
behind it.

The other thing that I want to make clear to everyone is that you have to make sure that the data tells you
the stories. Sometimes people think that data can answer everything and sometimes we have to
acknowledge that that is simply untrue. I recently worked with a state to figure out why people weren't
signing up for the benefits that they needed and deserved. We saw people coming to the site and where
they would sign up for those benefits and see if they're qualified. But for some reason there was something
stopping them from taking the step of actually signing up.

So I was able to look into it using Google Analytics to try to uncover what is stopping people from taking
the action of signing up for these benefits that they need and deserve. And so I go into Google Analytics, I
see people are going back between this service page and the unemployment page back to the service page,
back to the unemployment page. And so I came up with a theory that hey, people aren't finding the
information that they need in order to take the next step to see if they qualify for these services.

The only way that I can actually know why someone left the site without taking action is if I ask them. I
would have to survey them. Google Analytics did not give me the data that I would need to 100% back my
theory or deny it. So when you're explaining to your stakeholders, "Hey I have a theory. This data is telling
me a story. However I can't 100% know due to the limitations of data," You just have to say it. So the way
that I communicate that is I say "I have a theory that people are not finding the information that they need
in order to take action. Here's the proved points that I have that support that theory."

So what we did was we then made it a little bit easier to find that information. Even though we weren't
100% sure that my theory was correct, we were confident enough to take action and then we looked back,
and we saw all the metrics that pointed me to this theory improve. And so that always feels really good
when you're able to help a cause that you believe in do better, and help more people through data. It makes
all the nerdy learning about SQL and everything completely worth it.

Certainly! Here's the transcript arranged into paragraphs without any changes:

---
We live in a world that loves instant gratification, whether it's overnight delivery or on-demand movies.
We want what we want and we want it now. But in the data world, speed can sometimes be the enemy of
accuracy, especially when collaboration is required.

We're going to talk about how to balance speedy answers with right ones and how to best address these
issues by re-framing questions and outlining problems. That way your team members and stakeholders
understand what answers they can expect when.

As data analysts, we need to know the why behind things like a sales slump, a player's batting average, or
rainfall totals. It's not just about the figures, it's about the context too and getting to the bottom of these
things takes time.

So if a stakeholder comes knocking on your door, a lot of times that person may not really know what they
need. They just know they want it at light speed. But sometimes the pressure gets to us and even the most
experienced data analysts can be tempted to cut corners and provide flawed or unfinished data in the
interest of time.

When that happens, so much of the story in the data gets lost. That's why communication is one of the
most valuable tools for working with teams. It's important to start with structured thinking and a well-
planned scope of work, which we talked about earlier.

If you start with a clear understanding of your stakeholders' expectations, you can then develop a realistic
scope of work that outlines agreed upon expectations, timelines, milestones, and reports. This way, your
team always has a road map to guide their actions. If you're pressured for something that's outside of the
scope, you can feel confidence setting more realistic expectations.

At the end of the day, it's your job to balance fast answers with the right answers. Not to mention figuring
out what the person is really asking. Now seems like a good time for an example.

Imagine your VP of HR shows up at your desk demanding to see how many new hires are completing a
training course they've introduced. She says, "There's no way people are going through each section of the
course. The human resources team is getting slammed with questions. We should probably just cancel the
program." How would you respond?

Well, you could log into the system, crunch some numbers, and hand them to your supervisor. That would
take no time at all. But the quick answer might not be the most accurate one. So instead, you could re-
frame her question, outline the problem, challenges, potential solutions, and time-frame.
You might say, "I can certainly check out the rates of completion, but I sense there may be more to the
story here. Could you give me two days to run some reports and learn what's really going on?" With more
time, you can gain context. You and the VP of HR decide to expand the project timeline, so you can spend
time gathering anonymous survey data from new employees about the training course.

Their answers provide data that can help you pinpoint exactly why completion rates are so low. Employees
are reporting that the course feels confusing and outdated. Because you were able to take time to address
the bigger problem, the VP of HR has a better idea about why new employees aren't completing the course
and can make new decisions about how to update it.

Now the training course is easy to follow and the HR department isn't getting as many questions.
Everybody benefits. Redirecting the conversation will help you find the real problem which leads to more
insightful and accurate solutions.

But it's important to keep in mind, sometimes you need to be the bearer of bad news and that's okay.
Communicating about problems, potential solutions and different expectations can help you move forward
on a project instead of getting stuck.

When it comes to communicating answers with your teams and stakeholders, the fastest answer and the
most accurate answer aren't usually the same answer. But by making sure that you understand their needs
and setting expectations clearly, you can balance speed and accuracy. Just make sure to be clear and
upfront and you'll find success.

Limitations of data
Data is powerful, but it has its limitations. Has someone’s personal opinion found its way into
the numbers? Is your data telling the whole story? Part of being a great data analyst is
knowing the limits of data and planning for them. This reading explores how you can do that.

If you have incomplete or nonexistent data, you might realize during an analysis that you
don't have enough data to reach a conclusion. Or, you might even be solving a different
problem altogether! For example, suppose you are looking for employees who earned a
particular certificate but discover that certification records go back only two years at your
company. You can still use the data, but you will need to make the limits of your analysis
clear. You might be able to find an alternate source of the data by contacting the company
that led the training. But to be safe, you should be up front about the incomplete dataset until
that data becomes available.
If you're collecting data from other teams and using existing spreadsheets, it is good to keep
in mind that people use different business rules. So one team might define and measure things
in a completely different way than another. For example, if a metric is the total number of
trainees in a certificate program, you could have one team that counts every person who
registered for the training, and another team that counts only the people who completed the
program. In cases like these, establishing how to measure things early on standardizes the
data across the board for greater reliability and accuracy. This will make sure comparisons
between teams are meaningful and insightful.

Dirty data refers to data that contains errors. Dirty data can lead to productivity loss,
unnecessary spending, and unwise decision-making. A good data cleaning effort can help you
avoid this. As a quick reminder, data cleaning is the process of fixing or removing incorrect,
corrupted, incorrectly formatted, duplicate, or incomplete data within a dataset. When you
find and fix the errors - while tracking the changes you made - you can avoid a data disaster.
You will learn how to clean data later in the training.

Avinash Kaushik, a Digital Marketing Evangelist for Google, has lots of great tips for data
analysts in his blog: Occam's Razor. Below are some of the best practices he recommends for
good data storytelling:

 Compare the same types of data: Data can get mixed up when you chart it for
visualization. Be sure to compare the same types of data and double check that any
segments in your chart definitely display different metrics.
 Visualize with care: A 0.01% drop in a score can look huge if you zoom in close
enough. To make sure your audience sees the full story clearly, it is a good idea to set
your Y-axis to 0.
 Leave out needless graphs: If a table can show your story at a glance, stick with the
table instead of a pie chart or a graph. Your busy audience will appreciate the clarity.
 Test for statistical significance: Sometimes two datasets will look different, but you
will need a way to test whether the difference is real and important. So remember to
run statistical tests to see how much confidence you can place in that difference.
 Pay attention to sample size: Gather lots of data. If a sample size is small, a few
unusual responses can skew the results. If you find that you have too little data, be
careful about using it to form judgments. Look for opportunities to collect more data,
then chart those trends over longer periods.
In any organization, a big part of a data analyst’s role is making sound judgments. When you
know the limitations of your data, you can make judgment calls that help people make better
decisions supported by the data. Data is an extremely powerful tool for decision-making, but
if it is incomplete, misaligned, or hasn’t been cleaned, then it can be misleading. Take the
necessary steps to make sure that your data is complete and consistent. Clean the data before
you begin your analysis to save yourself and possibly others a great amount of time and
effort.

Certainly! Here's the transcript arranged into paragraphs without changing anything:

---

Data has the power to change the world. Think about this. A bank identifies 15 new
opportunities to promote a product, resulting in $120 million in revenue. A distribution
company figures out a better way to manage shipping, reducing their cost by $500,000.
Google creates a new tool that can identify breast cancer tumors in nearby lymph nodes.
These are all amazing achievements, but do you know what they have in common? They're
all the results of data analytics. You absolutely have the power to change the world as a data
analyst. And it starts with how you share data with your team.

In this video, we will think through all of the variables you should consider when sharing
data. When you successfully deliver data to your team, you can ensure that they're able to
make the best possible decisions. Earlier we learned that speed can sometimes affect accuracy
when sharing database information with a team. That's why you need a solid process that
weighs the outcomes and actions of your analysis.

So where do you start? Well, the best solutions start with questions. You might remember
from our last video, that stakeholders will have a lot of questions but it's up to you to figure
out what they really need. So ask yourself, does your analysis answer the original question?
Are there other angles you haven't considered? Can you answer any questions that may get
asked about your data and analysis?

That last question brings up something else to think about. How detailed should you be when
sharing your results? Would a high-level analysis be okay? Above all else, your data analysis
should help your team make better, more informed decisions.

Here is another example: Imagine a landscaping company is facing rising costs and they can't
stay competitive in the bidding process. One question you could ask to solve this problem is,
can the company find new suppliers without compromising quality? If you gave them a high-
level analysis, you'd probably just include the number of clients and cost of supplies.

Here your stakeholder might object. She's worried that reducing quality will limit the
company's ability to stay competitive and keep customers happy. Well, she's got a point. In
that case, you need to provide a more detailed data analysis to change her mind. This might
mean exploring how customers feel about different brands. You might learn that customers
don't have a preference for specific landscape brands. So the company can change to the more
affordable suppliers without compromising quality.

If you feel comfortable using the data to answer all these questions and considerations, you've
probably landed on a solid conclusion. Nice! Now that you understand some of the variables
involved with sharing data with a team, like process and outcome, you're one step closer to
making sure that your team has all the information they need to make informed, data-driven
decisions.

TEST

Amazing team work

Here's the transcript arranged into paragraphs:

---

Now it's time to discuss meetings. Meetings are a huge part of how you communicate with
team members and stakeholders. Let's cover some easy-to-follow do's and don'ts, you can use
for meetings both in person or online so that you can use these communication best practices
in the future.

At their core, meetings make it possible for you and your team members or stakeholders to
discuss how a project is going. But they can be so much more than that. Whether they're
virtual or in person, team meetings can build trust and team spirit. They give you a chance to
connect with the people you're working with beyond emails. Another benefit is that knowing
who you're working with can give you a better perspective of where your work fits into the
larger project. Regular meetings also make it easier to coordinate team goals, which makes it
easier to reach your objectives. With everyone on the same page, your team will be in the
best position to help each other when you run into problems too.

Whether you're leading a meeting or just attending it, there are best practices you can follow
to make sure your meetings are a success. There are some really simple things you can do to
make a great meeting. Come prepared, be on time, pay attention, and ask questions. This
applies to both meetings you lead and ones you attend. Let's break down how you can follow
these to-dos for every meeting.

What do I mean when I say come prepared? Well, a few things. First, bring what you need. If
you like to take notes, have your notebook and pens in your bag or your work device on hand.
Being prepared also means you should read the meeting agenda ahead of time and be ready to
provide any updates on your work. If you're leading the meeting, make sure to prepare your
notes and presentations and know what you're going to talk about and of course, be ready to
answer questions.

These are some other tips that I like to follow when I'm leading a meeting. First, every
meeting should focus on making a clear decision and include the person needed to make that
decision. And if there needs to be a meeting in order to make a decision, schedule it
immediately. Don't let progress stall by waiting until next week's meeting. Lastly, try to keep
the number of people at your meeting under 10 if possible.

More people makes it hard to have a collaborative discussion. It's also important to respect
your team members' time. The best way to do this is to come to meetings on time. If you're
leading the meeting, show up early and set up beforehand so you're ready to start when
people arrive. You can do the same thing for online meetings. Try to make sure your
technology is working beforehand and that you're watching the clock so you don't miss a
meeting accidentally.

Staying focused and attentive during a meeting is another great way to respect your team
members' time. You don't want to miss something important because you were distracted by
something else during a presentation. Paying attention also means asking questions when you
need clarification, or if you think there may be a problem with a project plan. Don't be afraid
to reach out after a meeting. If you didn't get to ask your question, follow up with the group
afterwards and get your answer.

When you're the person leading the meeting, make sure you build and send out an agenda
beforehand, so your team members can come prepared and leave with clear takeaways. You'll
also want to keep everyone involved. Try to engage with all your attendees so you don't miss
out on any insights from your team members. Let everyone know that you're open to
questions after the meeting too. It's a great idea to take notes even when you're leading the
meeting.

This makes it easier to remember all questions that were asked. Then afterwards you can
follow up with individual team members to answer those questions or send an update to your
whole team depending on who needs that information. Now let's go over what not to do in
meetings. There are some obvious "don'ts" here. You don't want to show up unprepared, late,
or distracted for meetings. You also don't want to dominate the conversation, talk over others,
or distract people with unfocused discussion.

Try to make sure you give other team members a chance to talk and always let them finish
their thought before you start speaking. Everyone who is attending your meeting should be
giving their input. Provide opportunities for people to speak up, ask questions, call for
expertise, and solicit their feedback. You don't want to miss out on their valuable insights.
And try to have everyone put their phones or computers on silent when they're not speaking,
you included.

Now we've learned some best practices you can follow in meetings like come prepared, be on
time, pay attention, and ask questions. We also talked about using meetings productively to
make clear decisions and promoting collaborative discussions and to reach out after a
meeting to address questions you or others might have had. You also know what not to do in
meetings: showing up unprepared, late, or distracted, or talking over others and missing out
on their input. With these tips in mind, you'll be well on your way to productive, positive
team meetings.

But of course, sometimes there will be conflict in your team. We'll discuss conflict resolution
soon.

Ximena: Joining a new team

Save note
TranscriptNotesDownloadsDiscuss
Interactive Transcript - Enable basic transcript mode by
pressing the escape key
You may navigate through the transcript using tab. To save a note for a section of text press CTRL + S. To
expand your selection you may use CTRL + arrow key. You may contract your selection using shift +
CTRL + arrow key. For screen readers that are incompatible with using arrow keys for shortcuts, you can
replace them with the H J K L keys. Some screen readers may require using CTRL in conjunction with the
alt key
Play video starting at :: and follow transcript0:00
[MUSIC]
Joining a new team was definitely scary at the beginning.
Especially at a company like Google where it's really big and
everyone is extremely smart.
But I really leaned on my manager to understand what I could bring to
the table.
And that made me feel a lot more comfortable in meetings while sharing my
abilities.
I found that my best projects start off when the communication is really clear
about what's expected.
If I leave the meeting where the project has been
asked of me knowing exactly where to start and what I need to do,
that allows for me to get it done faster, more efficiently, and
getting to the real goal of it
and maybe going an extra step further because I didn't have to spend any time
confused on what I needed to be doing.
Communication is so important because it gets you to the finish line the most
efficiently and also makes you look really good.
When I first started I had a good amount of projects thrown at me and
I was really excited.
So, I went into them without asking too many questions.
At first that was an obstacle, because while you can thrive in ambiguity,
ambiguity as to what the project objective is, can be really harmful
when you're actually trying to get the goal done.
And I overcame that by simply taking a step back when someone asks me to do
the project and just clarifying what that goal was.
Once that goal was crisp,
I was happy to go into the ambiguity of how to get there,
but the goal has to be really objective and clear.
I'm Ximena and I'm a Financial Analyst.

Lead great meetings

One day soon, you might find yourself planning a meeting in your role as a data analyst.
Great things can happen when participants anticipate a well-executed meeting. Attendees
show up on time. They aren’t distracted by their laptops and phones. They feel like their time
will be well spent. It all comes down to good planning and communication of
expectations. The following are our best practical tips for leading meetings.

Before the meeting

If you are organizing the meeting, you will probably talk about the data. Before the meeting:

 Identify your objective. Establish the purpose, goals, and desired outcomes of the
meeting, including any questions or requests that need to be addressed.
 Acknowledge participants and keep them involved with different points of view and
experiences with the data, the project, or the business.
 Organize the data to be presented. You might need to turn raw data into accessible
formats or create data visualizations.
 Prepare and distribute an agenda. We will go over this next.

Crafting a compelling agenda

A solid meeting agenda sets your meeting up for success. Here are the basic parts your
agenda should include:
  Meeting start and end time
 Meeting location (including information to participate remotely, if that option is
available)
 Objectives
 Background material or data the participants should review beforehand
Here's an example of an agenda for an analysis project that is just getting started:

Sharing your agenda ahead of time

After writing your agenda, it's time to share it with the invitees. Sharing the agenda with
everyone ahead of time helps them understand the meeting goals and prepare questions,
comments, or feedback. You can email the agenda or share it using another collaboration
tool.

During the meeting

As the leader of the meeting, it's your job to guide the data discussion. With everyone well
informed of the meeting plan and goals, you can follow these steps to avoid any distractions:

 Make introductions (if necessary) and review key messages

 Present the data
 Discuss observations, interpretations, and implications of the data
 Take notes during the meeting
 Determine and summarize next steps for the group

After the meeting

To keep the project and everyone aligned, prepare and distribute a brief recap of the meeting
with next steps that were agreed upon in the meeting. You can even take it a step further by
asking for feedback from the team.

 Distribute any notes or data

 Confirm next steps and timeline for additional actions
 Ask for feedback (this is an effective way to figure out if you missed anything in your
recap)

A final word about meetings

Even with the most careful planning and detailed agendas, meetings can sometimes go off
track. An emergency situation might steal people’s attention. A recent decision might
unexpectedly change requirements that were previously discussed and agreed on. Action
items might not apply to the current situation. If this happens, you might be forced to shorten
or cancel your meeting. That's all right; just be sure to discuss anything that impacts your
project with your manager or stakeholders and reschedule your meeting after you have more
information.

Here's the transcript arranged into paragraphs:

---

It's normal for conflict to come up in your work life. A lot of what you've learned so far, like
managing expectations and communicating effectively can help you avoid conflict, but
sometimes you'll run into conflict anyways. If that happens, there are ways to resolve it and
move forward.

In this video, we will talk about how conflict could happen and the best ways you can
practice conflict resolution. A conflict can pop up for a variety of reasons. Maybe a
stakeholder misunderstood the possible outcomes for your project; maybe you and your team
member have very different work styles; or maybe an important deadline is approaching and
people are on edge. Mismatched expectations and miscommunications are some of the most
common reasons conflicts happen.

Maybe you weren't clear on who was supposed to clean a dataset and nobody cleaned it,
delaying a project. Or maybe a teammate sent out an email with all of your insights included,
but didn't mention it was your work. While it can be easy to take conflict personally, it's
important to try and be objective and stay focused on the team's goals.

Believe it or not, tense moments can actually be opportunities to re-evaluate a project and
maybe even improve things. So when a problem comes up, there are a few ways you can flip
the situation to be more productive and collaborative. One of the best ways you can shift a
situation from problematic to productive is to just re-frame the problem.

Instead of focusing on what went wrong or who to blame, change the question you're starting
with. Try asking, how can I help you reach your goal? This creates an opportunity for you
and your team members to work together to find a solution instead of feeling frustrated by the
problem. Discussion is key to conflict resolution.

If you find yourself in the middle of a conflict, try to communicate, start a conversation or
ask things like, are there other important things I should be considering? This gives your team
members or stakeholders a chance to fully lay out your concerns. But if you find yourself
feeling emotional, give yourself some time to cool off so you can go into the conversation
with a clearer head.

If I need to write an email during a tense moment, I'll actually save it to drafts and come back
to it the next day to reread it before sending to make sure that I'm being level-headed. If you
find you don't understand what your team member or stakeholder is asking you to do, try to
understand the context of their request. Ask them what their end goal is, what story they're
trying to tell with the data or what the big picture is.

By turning moments of potential conflict into opportunities to collaborate and move forward,
you can resolve tension and get your project back on track. Instead of saying, "There's no
way I can do that in this time frame," try to re-frame it by saying, "I would be happy to do
that, but I'll just take this amount of time, let's take a step back so I can better understand
what you'd like to do with the data and we can work together to find the best path forward."

With that, we've reached the end of this section. Great job. Learning how to work with new
team members can be a big challenge in starting a new role or a new project but with the
skills you've picked up in these videos, you'll be able to start on the right foot with any new
team you join.

So far, you've learned about balancing the needs and expectations of your team members and
stakeholders. You've also covered how to make sense of your team's roles and focus on the
project objective, the importance of clear communication and communication expectations in
a workplace, and how to balance the limitations of data with stakeholder asks.

Finally, we covered how to have effective team meetings and how to resolve conflicts by
thinking collaboratively with your team members. Hopefully now you understand how
important communication is to the success of a data analyst. These communication skills
might feel a little different from some of the other skills you've been learning in this program,
but they're also an important part of your data analyst toolkit and your success as a
professional data analyst.

Just like all of the other skills you're learning right now, your communication skills will grow
with practice and experience.

Here's the transcript arranged into paragraphs:

---

Hey, I'm Nathan. I'm a principal data analyst in the Trust and Safety Organization at Google. I joined the
Marine Corps Reserves when I was attending college, and the reserve unit I joined was a field artillery
unit. So after a challenging Marine Corps boot camp, I went to field artillery fire direction control school.
And for those of you that might not know, fire direction control is considered the brains of field artillery,
and we use all sorts of computers to do our artillery calculations. But just in case the computers went
down, we also were trained how to use slide rules as a backup.

A year later, I had the opportunity to be activated as a truck driver instead of my primary job as a field
artillery man and was deployed to Iraq to drive trucks for an infantry company. After I got back from Iraq,
I finished up my bachelor's degree and then worked as an applications engineer in Austin, Texas, and
eventually saw the need to pivot more to focus more on business. And that's when I really fell in love with
data analysis was when I was learning a lot more about business.

It actually took me a couple of years, when I really sparked an interest in data analysis to land a role where
I got to do it full time and really get my hands dirty with the data. Some of the things I did to lay the
groundwork to be ready and be qualified for that was I took a Coursera course on R and I also did some
data science hackathons where you spend an entire weekend at some university. And they release the
dataset Friday night and by Sunday afternoon, you have to come up with some recommendations. So those
were two really good ways to really prepare myself, get good experience and really show a strong interest
in data analysis.

My first job, where I got to do data analysis full-time was at a large bank and I was just in heaven. I got to
really do SQL for real, and also I got to use Tableau a ton. Got to go to a Tableau conference. It was really
cool. Then I was fortunate enough to get an opportunity to move to Google into my current role. That's in
trust and safety. And what's super exciting and fulfilling about that is that similar to the military, it has an
overall mission of protecting people, so that's super exciting for me.

The things that were instilled in me in the Marines that I use to this very day would be attention to detail.
That's super important in the military overall, but especially in field artillery. Secondly, is the importance
of communication. You have your own details locked in. You need to make sure that those are
communicated really clearly to other people that you're working with and the third would be collaboration.
In the military teamwork makes the dream work. You really rely on the team. That's definitely been the
case in my post Marine Corps career and jobs.