BUS 4055 Week 5: Quantitative Data

Analysis
Kevin Brennan, M.Mgt.

Photo by Claudio Schwarz on Unsplash

Introduction to Quantitative
Data
– Objective: Understand how quantita‐
tive data is processed and analyzed to
turn raw data into meaningful informa‐
tion.
– Key Point: Raw data is often mean‐
ingless without processing.
Photo by Mika Baumeister on Unsplash
– Methods: Quantitative techniques like
graphs, charts, and statistics help de‐
scribe and explore relationships in data.
– Discussion: Discuss how quantitative data is typically used to make decisions in
business research.
– Example: Student satisfaction survey results, sales data, or website traffic analy‐
sis.

Importance of Quantitative
Data in Business Research
– Business Application: Quantitative
data provides the backbone for decision-
making in business, from budgeting to
customer satisfaction surveys.
– Common Examples: Frequencies,
test scores, prices, rental costs, or stu‐
Photo by Victoriano Izquierdo on Unsplash
dent feedback.
– Key Focus: Identifying trends, testing
hypotheses, and making data-driven decisions.
– Discussion: How businesses use quantitative data to drive decisions in fields
like finance, marketing, and operations.
– Example: Evaluating a company's customer service based on the number of re‐
solved support tickets or customer ratings.
Overview of Data Types
– Key Data Types:
– Categorical: Non-numerical data used
for classification (e.g., gender, product
categories).
– Numerical: Data that can be counted
Source: https://stackoverflow.com/ques‐
or measured (e.g., age, income).
tions/34095777/handling-unassigned-null-values-of-cat‐
– Discussion: Explain the difference
egorical-features-in-regression-machine
between categorical and numerical data
and when each is used.
– Example: Survey responses about satisfaction levels using categories like "Very
Satisfied" or numerical ratings from 1 to 5.

Categorical Data
– Definition: Data used to classify ob‐
servations into distinct categories with‐
out numerical meaning.
– Key Properties: No intrinsic numerical
relationship (e.g., car models, survey
responses).
– Discussion: Categorical data is help‐
ful in classifying observations into
Baijayanta Roy, https://towardsdata‐ groups.
science.com/all-about-categorical-variable- – Example: Analyzing survey results to
encoding-305f3361fd02 see the number of students who use
specific college resources, such as the
library or counselling services.
Nominal Data
– Definition: A categorical data type where categories are named but have no in‐
trinsic order.
– Key Features: No ranking or order among categories (e.g., gender, departments,
or colors).
– Discussion: Nominal data provides labels to classify variables without assigning
them any order or value.
– Example: Classifying survey respondents by their department (e.g., Engineering,
Business, Arts).
Ordinal Data
– Definition: Categorical data where the categories have a meaningful order or
rank but uneven intervals.
– Key Properties: Data points can be ranked, but differences between points are
not equal.
– Discussion: Ordinal data is useful for ranking but cannot precisely measure the
difference between ranks.
– Example: Customer satisfaction ratings: "Very Satisfied," "Satisfied," and "Unsat‐
isfied," where each category reflects increasing satisfaction.
Numerical Data: Discrete vs. Continuous
– Discrete Data: Countable, often finite
(e.g., number of students in a class).
– Continuous Data: Measurable, can
take any value within a range (e.g.,
weight, distance).
– Key Focus: Discrete data represent
Source: https://betterexplained.com/articles/under‐
standing-discrete-vs-continuous-growth/ whole numbers, while continuous data
can represent fractions.
– Example: Discrete - Number of products sold; Continuous - Sales revenue over
time.
– Discussion: Which type of data would be most useful in measuring student suc‐
cess?

Interval Data
– Definition: Numerical data where the
intervals between values are meaningful,
but there is no true zero.
– Key Properties: Can add or subtract
values, but ratios are meaningless (e.g.,
20°C is not twice as warm as 10°C).
– Use: Typically used when differences
between values are meaningful, but
comparisons using ratios are not.
– Example: Temperature, SAT scores.
– Discussion: What situations would
require using interval data, and what are
Source: http://reliawiki.com/index.php/Interval_‐
its limitations?
Data_Example

Ratio Data
– Definition: Numerical data that includes a true zero point, allowing for meaning‐
ful ratios.
– Key Properties: Ratios are meaningful (e.g., someone earning $100K earns
twice as much as someone earning $50K).
– Use: Ratios can be compared directly because of the presence of a true zero
point.
– Example: Income, age, weight.
– Discussion: Why is ratio data important when comparing quantitative variables
like income or population?
 Source: https://careerfoundry.‐
com/en/blog/data-analytics/what-is-ratio-
data/

Data Collection Methods

– Surveys: Widely used in quantitative
research to gather large amounts of
data.
– Questionnaires: Typically used to
capture structured responses.
– Discussion: How choosing the right
data collection method affects the type
and quality of data collected.
– Example: A student satisfaction sur‐
vey using a Likert scale to quantify their
Photo by Scott Graham on Unsplash
responses about services like tutoring or
library access.

Preparing Data for Analysis

– Data Cleaning: Removing errors, du‐
plicates, and inconsistencies in data.
– Data Coding: Converting categorical
responses into numerical values for eas‐
Data Preparation Data Analytics

ier analysis.
Raw Data Prepared Data Insights – Importance: Clean data leads to accu‐
rate results and reduces bias.
– Example: Cleaning a student survey
dataset by standardizing responses to
ensure consistency before analysis.
– Discussion: Why is data cleaning an
Source: https://devopedia.org/data-prepa‐ essential step in the research process?
ration Coding Categorical Data
–
 Data Matrix: A table where rows represent cases (individual responses) and col‐
umns represent variables.
–
Data Organization: Each row in the matrix represents a respondent, and each col‐
umn a survey question.
–
Use: A data matrix organizes data in a structured way, making it easier to perform
analysis.
–
Example: A matrix displaying survey responses, with rows for individual students
and columns for satisfaction ratings.
–
Discussion: How does organizing your data in a matrix improve data analysis effi‐
ciency?
–
Categorical Coding: Assigning numerical values to categorical data (e.g., 1 =
Male, 2 = Female).
–
Codebook: A reference guide that explains each numerical code and its meaning.
–
Importance: Coding allows easier manipulation and analysis of non-numerical
data.
–
Example: Coding student satisfaction responses on a scale of 1-5, with 1 meaning
"Very Dissatisfied" and 5 "Very Satisfied."
–
Discussion: What are the potential pitfalls of incorrect data coding?
Data Visualization
– Purpose: Graphs and charts make
data easier to understand and communi‐
cate to stakeholders.
– Common Graph Types:
– Bar Chart: Compare categorical data
(e.g., number of students per major).
– Line Graph: Track changes over time
(e.g., enrollment rates).
– Scatterplot: Show relationships be‐
tween variables (e.g., hours studied vs.
GPA).
– Example: A line graph showing the trend of student satisfaction over multiple se‐
mesters.
– Discussion: Why is visualization important in data analysis? How do different
types of graphs help convey specific types of information?

Organizing Data: Frequency Tables

 – Definition: Frequency tables display
the number of occurrences of each cate‐
gory or value in a dataset.
– Purpose: Helps summarize data and
identify patterns or trends.
– Use: Frequency tables help visualize
and simplify categorical data.
– Example: A frequency table showing
Source: https://edu.gcfglobal.org/en/sta‐ how many students rated their satisfac‐
tistics-basic-concepts/frequency-tables/1/ tion level as 1, 2, 3, etc.
– Discussion: How does a frequency
table help understand the distribution of categorical responses?

Bar Charts
– Definition: Bar charts visually repre‐
sent categorical data by using bars to
show the frequency of each category.
– Purpose: Makes it easy to compare
the number of occurrences in different
categories.
– Use: Bar charts are particularly useful
for showing differences between groups
or categories.
– Example: A bar chart displaying the
number of students from each major
(e.g., Business, Engineering, Arts).
– Discussion: Why are bar charts effec‐
tive for comparing categorical data in
© Ladislav Kubačka business analysis?

Histograms
– Definition: Histograms represent the distribution of continuous data by using ad‐
jacent bars to show frequencies in intervals.
– Purpose: Useful for understanding the shape of data distributions (normal,
skewed, etc.).
– Use: Typically used to show how frequently different ranges of values occur in a
dataset.
– Example: A histogram showing the distribution of student ages in a survey sam‐
ple.
– Discussion: How does the shape of a histogram help in understanding data pat‐
terns?
av danielpenfield - eget arbete, cc by-sa 3.0,
https://commons.wikimedia.org/w/index.php?
curid=9401898

Pie Charts
– Definition: Pie charts divide a circle
into slices to represent proportions of a
whole.
– Purpose: Best used to show the rela‐
tive sizes of categories.
– Use: Common for visualizing categori‐
cal data where percentages or propor‐
tions are relevant.
– Example: A pie chart showing the per‐
centage of students using different cam‐
pus services.
– Discussion: When is a pie chart more
effective than a bar chart, and what limi‐
tations might it have?

https://infogram.com/blog/choose-the-right-
chart/

Measures of Central Tendency: Mean

– Definition: The mean (or average) is the sum of all data points divided by the
number of points.
– Use: Provides a "typical" value for a dataset, especially useful for numerical data.
 – Key Point: Sensitive to outliers; ex‐
treme values can skew the mean.
– Example: Calculating the average sat‐
isfaction score from student feedback,
where scores range from 1 to 5.
– Discussion: When is the mean a reli‐
able indicator of central tendency, and

source: https://faculty.elgin.edu/dkernler/sta‐when might it be misleading?

tistics/ch03/3-1.html

Measures of Central Tendency: Median

– Definition: The median is the middle
value when data points are arranged in
order.
– Use: Provides a central point that is
less affected by outliers than the mean.
– Key Point: Useful for skewed distribu‐
tions where the mean might not be rep‐
resentative.
– Example: Median income levels in a
survey of student financial aid recipients.
– Discussion: How does the median
help provide a clearer picture when the
data includes extreme values?
https://opentextbc.ca/mediastudies101/chapter/political-
economies-of-digital-media/

Measures of Central Tendency: Mode

– Definition: The mode is the most frequent value in a dataset.
– Use: Helps identify the most common value, especially useful for categorical
data.
– Example: Finding the most common satisfaction rating on a student course feed‐
back form.
– Discussion: In what scenarios is the mode more informative than the mean or
median?
https://faculty.elgin.edu/dkernler/statistics/ch03/3-
1.html

Graphical Representation of Central Tendency

– Purpose: Visualize key summary sta‐
tistics such as mean, median, and mode.
– Graph Types:
– Box Plot: Shows the distribution, high‐
lighting the median and quartiles.
– Line Chart: Displays changes over
time.
– Example: A box plot showing the dis‐
https://ledidi.com/academy/measures-of-
tribution of test scores among students
central-tendency-mean-median-and-mode
in different departments.
– Discussion: How does visualizing
measures of central tendency aid in understanding data? Discuss the value of us‐
ing box plots versus line charts.

Measures of Dispersion: Range

– Definition: The range is the difference between the highest and lowest values in
a dataset.
– Use: Provides a basic measure of variability within a dataset.
– Key Point: The range is limited as it only considers the two extreme values.
– Example: The range of student GPAs in a sample from 2.0 to 4.0.
– Discussion: What are the limitations of using range as the sole measure of dis‐
persion?
 Source: https://sixsigmadsi.com/range-
measure-of-dispersion/

Measures of Dispersion: Standard Deviation

– Definition: Standard deviation mea‐
sures the average distance of each data
point from the mean.
– Use: Helps understand the spread of
data, with a small standard deviation in‐
dicating that data points are close to the
mean.
– Key Point: Provides a more nuanced
view of variability compared to the
source: https://opentextbc.ca/mediastudies101/chap‐
range.
ter/political-economies-of-digital-media/
– Example: Calculating the standard de‐
viation of test scores in a class to see
how much variation exists in student performance.
– Discussion: Why is standard deviation preferred over range for understanding
data variability?

Graphical Representation of Dispersion

– Purpose: Use graphs to show the
spread or variability of data.
– Graph Types:
– Histogram: Visualizes the frequency
distribution of continuous data.
– Box Plot: Highlights the range, quar‐
tiles, and potential outliers.
– Example: A histogram showing the
distribution of student ages across the
college.
Source: http://derekogle.com/Book107/Univ‐ – Discussion: Why is it important to vi‐
EDA.html sualize data variability? How do graphs
like histograms provide insights into pat‐
 terns not easily seen in raw data?

Multivariate Analysis
– Definition: Multivariate analysis in‐
volves examining more than two vari‐
ables simultaneously to understand the
relationships between them.
– Use: Common in business research to
explore complex interactions between
variables.
– Example: Examining how age, in‐
http://www.sthda.com/english/articles/32-r-
come, and education level affect student
graphics-essentials/129-visualizing-multi‐
satisfaction with college services.
variate-categorical-data/
– Discussion: What are the benefits
and challenges of using multivariate
analysis in business research?

Statistical Significance
– Definition: Statistical significance as‐
sesses whether results from data are
meaningful or could have occurred by
chance.
– Key Concept: The p-value is com‐
monly used to determine significance
(e.g., p < 0.05 means the result is statis‐
tically significant).
– Use: Ensures that the findings of a
Source: https://researcher.life/blog/arti‐ study are not random and can be gener‐
cle/what-is-p-value-calculation-statistical- alized to the population.
significance/ – Example: Testing whether differences
in satisfaction between two groups of
students (e.g., online vs. in-person) are statistically significant.
– Discussion: Why is it important to test for statistical significance in business re‐
search?

Chi-Square Test
– Definition: A chi-square test is used to determine whether there is a significant
association between two categorical variables.
– Use: Commonly applied in surveys and observational studies.
– Example: Testing whether student satisfaction is related to their year of study
(e.g., freshman, sophomore, junior).
– Key Concept: The test compares observed frequencies with expected frequen‐
cies under the assumption that there is no association.
 – Discussion: What types of research
questions can the chi-square test help
answer?

By Mikael Häggström - File:Chi-square distri‐

butionCDF.png, Public Domain, https://com‐
mons.wikimedia.org/w/index.php?
curid=10633630

T-Test

Title
By Cornell User 2 - Own work, CC0,
https://commons.wikimedia.org/w/index.php?
curid=140537163
– Definition: A t-test compares the means of two groups to determine if there is a
statistically significant difference between them.
– Use: Commonly used to compare two groups in experiments or surveys.
– Example: Comparing the average test scores of students who received tutoring
versus those who did not.
– Key Concept: A low p-value (< 0.05) suggests the difference between the two
groups is statistically significant.
– Discussion: When should a t-test be used, and what are its limitations?

Analysis of Variance (ANOVA)

– Definition: ANOVA tests whether there are statistically significant differences be‐
tween the means of three or more groups.
– Use: Useful for comparing multiple groups or conditions in experiments.
–
 Example: Comparing the effectiveness
of different teaching methods across
multiple classes.
Key Concept: If the p-value from ANOVA
is low, it suggests that at least one group
mean is significantly different from the
others.
– Discussion: When is ANOVA more
appropriate than a t-test?

Identifying Trends in Data

– Purpose: Look for patterns or trends
that can provide insights into business
processes or customer behaviour.
– Methods:
– Line Graphs: Show trends over time.
– Scatterplots: Identify relationships be‐
tween variables.
– Example: Identifying a trend in student
participation rates in campus events
over multiple semesters.
– Discussion: Why is it important to
Source: https://pressbooks.senecacollege.ca/operationsmanagement/chap‐
identify trends in business data? Discuss
ter/forecasting/
how trends can inform strategic deci‐
sion-making.

Correlation Analysis
– Definition: Correlation measures the
strength and direction of the relationship
between two continuous variables.
– Use: Helpful in identifying relationships
but does not imply causality.
– Example: Investigating whether
there’s a correlation between the number
of hours students study and their GPA.
– Key Concept: A positive correlation
indicates both variables increase togeth‐
source: https://statistics.laerd.com/statisti‐
er, while a negative correlation means
cal-guides/pearson-correlation-coefficient-
one decreases as the other increases.
statistical-guide.php
– Discussion: How can correlation
analysis help identify trends, and what
are its limitations?
Regression Analysis
– Definition: Regression analysis exam‐
ines the relationship between a depen‐
dent variable and one or more indepen‐
dent variables.
– Use: Common in predictive modeling,
allowing researchers to forecast out‐
comes based on known variables.
– Example: Predicting student success
based on variables like hours studied,
attendance, and prior academic perfor‐
mance.
– Key Concept: Multiple regression al‐
lows for the inclusion of several independent variables to predict the outcome.
– Discussion: Why is regression analysis valuable for making predictions in busi‐
ness research, and what are the assumptions?
–

Week 5: Quantitative Data Analysis - Expanded Content

(Slides 31-45)

Common Pitfalls in Quantitative Data Analysis

– Key Pitfalls:
– Misinterpreting Correlations: Re‐
member, correlation does not imply cau‐
sation.
– Sampling Bias: Ensure that your sam‐
ple accurately represents the population.
– Overfitting: Avoid too many variables
in regression models, which can lead to
overfitting.
– Example: Assuming that increased
hours of study directly cause higher
GPAs without considering other factors.
Source: https://www.frontiersin.org/articles/10.3389/fda‐
– Discussion: How can you avoid com‐
ta.2019.00013/full
mon pitfalls in your own research? Dis‐
cuss strategies for ensuring data accura‐
cy and integrity.

Ethical Considerations in Quantitative Research

– Key Principles:
 – Data Privacy: Protect the anonymity
and confidentiality of participants.
– Informed Consent: Ensure partici‐
pants understand how their data will be
used.
– Data Integrity: Avoid manipulating
data to fit preconceived hypotheses.
– Example: Ensuring that student feed‐
back data is anonymized before analy‐
sis.
Photo by Isaac Smith on Unsplash
– Discussion: What ethical dilemmas
might arise in quantitative research, and
how can they be mitigated? Discuss potential consequences of unethical data
practices.

Key Takeaways from Week 5

– Recap: Review the most important
concepts covered in the week, including
data types, statistical tests, and visual‐
izations.
– Applications: Discuss how these con‐
cepts will apply to the final project and
real-world research scenarios.
– Activity: Have students list out the
methods they plan to use in their own
research projects.
Photo by Aldin Nasrun on Unsplash
– Discussion: What areas do you feel
most confident about, and what areas
need more clarification?

Next Steps for Research Project Preparation

– Action Items:
– Refine Your Research Questions: Ensure they are clear and measurable.
– Start Data Collection: Begin gathering and organizing your data.
– Preliminary Analysis: Perform initial tests to explore your data.
– Discussion: What is your timeline for completing the analysis phase of your
project? What challenges do you anticipate?
Photo by Kier in Sight Archives on Un‐
splash