DAL Workshop 2
DAL Workshop 2
Data Analytics for Leaders
Workshop 2
Background:
This workshop focuses on the concepts of confidence intervals and hypothesis testing. These are
important tools when estimating an average value for a whole population based on results from a
sample. For example, if we would like to know the average spending of our supermarket customers
and we can only survey few customers, then we would like to understand how accurately the mean
of this sample of customers estimates the mean of all our customers. The 95% confidence interval
gives us a range around the sample mean such that we are 95% confident that the mean spending of
all customers is within this range. Sometimes we would like to find out whether a statement about
the mean spending of all customers is likely to be true or not, e.g. “the mean spending of all
customers is €50 per visit”. Then by using hypothesis testing we can either reject or not reject this
hypothesis, at a specific significance level (e.g. 5%, corresponding to 95% confidence).
Financial Return Analysis
In this exercise you will analyse monthly financial log returns for three companies, Amazon, Apple
and Tesla, and for the FTSE market index.
Step 1: Load the data file
The data file for the returns is Financial_Returns.xlsx.
Step 2: Calculate summary statistics for the returns
From the Data menu, select Data Analysis… in the Data Analysis dialog box (shown below) select
Descriptive Statistics and press OK (or double‐click).
1
Exhibit 1: The Data Analysis dialog box
Specify the parameters to the descriptive statistics procedure:
Place the focus in the Input Range box by clicking in the white box. Then either:
1. select the data on the underlying spreadsheet using the mouse (i.e. select B1 and drag down
to B59) or,
2. specify the range directly by typing B1:B59
Specify that data is grouped in columns by clicking on the top button.
Tick the box to say that we have “Labels in the first row”.
Towards the bottom of the dialog box choose the Output Option: New Worksheet Ply, and give the
results worksheet the title “FTSE”.
Tick the box that specifies Summary Statistics. Also tick the box that specifies Confidence Level for
Mean.
2
Exhibit 2: The parameters for the Descriptive Statistics procedure
The dialog box should now look like Exhibit 2. Perform the analysis by pressing the OK button. Excel
will create a new worksheet with the results and call it “FTSE”.
Step 3: Examine the results of the descriptive analysis
Firstly, you can resize and reformat the columns so that you can see the results properly. The table
gives the summary statistics for the return figures of FTSE.
Pay particular attention to the following statistics:
Mean ‐ this is the average monthly return
St. deviation ‐ this measures the variability of the monthly returns around the mean
Minimum ‐ lowest monthly return
Maximum ‐ highest monthly return
Count ‐ number of observations in the sample
Your results should be similar as Exhibit 3 below:
3
Exhibit 3: Summary statistics for FTSE returns
Why don’t we have any value for Mode?
Step 4: Repeat the analysis for Amazon, Apple and Tesla
You can either repeat the steps above or select all the data columns to do the descriptive analysis for
all of them at the same time.
Step 5: Construct 95% confidence intervals for the mean of each series
Construct 95% confidence intervals by adding and subtracting 2 times the standard error, from the
mean. For example for FTSE: [‐0.13 – 2 ∙ 0.48, ‐0.13 + 2 ∙ 0.48]
You can also construct an accurate confidence interval by adding and subtracting from the mean the
“Confidence Level” number from the Descriptive Statistics output. For example for FTSE: [‐0.13 –
0.96, ‐0.13 + 0.96]
Step 6: Is the mean return zero?
For each series, can you reject the null hypothesis that the mean return is zero (use a 5% significance
level)?
Step 7: Apple’s return
Can you reject the assertion that Apple returns are 2% on average (use a 5% significance level)?
4
Step 8: Comparison of returns
Is it reasonable to say that there is no significant difference between the mean of Apple and Tesla
returns (use a 5% significance level)?
You can answer this question by comparing the two confidence intervals OR by using one of Excel’s
hypothesis testing tools: Tools…Data Analysis…t‐test: Two Sample Assuming Unequal Variances.