Assignment 10 - Session 14
WSES Case - Hypothesis testing
Example Hypothesis tested
1. One-Sample t-test
A one-sample t-test is used to determine whether the mean of a single sample is statistically
different from a known or hypothesized population mean.
Variable 1: Sales Value in Million
This test checks the marketing team's belief that the "average size of a deal is at least 8
million USD".
● Null Hypothesis (H0): The true average size of a deal is equal to $8 million.
H0:μ=8
● Alternate Hypothesis (Ha): The true average size of a deal is not equal to $8 million.
Ha:μ≠8
● Result and Significance: The analysis of the 1000 opportunities in the dataset shows
that the sample mean sales value is approximately $8.36 million. The t-statistic is 4.91
and the p-value is extremely small (approximately 1.0×10−6). Since the p-value is less
than the standard significance level of 0.05, we reject the null hypothesis. This
provides strong evidence that the true average size of a deal at WSES is significantly
different from $8 million.
Variable 2: Profit %
This test can assess if the average profit percentage is different from a hypothetical target of
50%.
● Null Hypothesis (H0): The true average profit percentage of a deal is 50%.
H0:μ=50
● Alternate Hypothesis (Ha): The true average profit percentage of a deal is not 50%.
Ha:μ≠50
● Result and Significance: The sample mean profit percentage is 50.29%. The t-statistic
is 0.86 and the p-value is 0.39. Because the p-value (0.39) is greater than 0.05, we fail
to reject the null hypothesis. There is not enough statistical evidence to conclude that
the true average profit percentage is different from 50%.
2. Independent Samples t-test
An independent samples t-test compares the means of two independent groups. Here, we
test the hypothesis that the average deal size in the UK is different from that in Africa.
● Variable for Test: The continuous variable to be tested is Sales Value in Million.
● Groups: The data is split into two independent groups based on the Region variable:
○ Group 1: Deals in the UK region.
○ Group 2: Deals in the Africa region.
● Hypotheses:
○ Null Hypothesis (H0): There is no difference in the mean sales value between deals in
the UK and deals in Africa.
H0:μUK=μAfrica
○ Alternate Hypothesis (Ha): There is a significant difference in the mean sales value
between deals in the UK and deals in Africa.
Ha:μUK≠μAfrica
● Result and Significance: The mean sales value for deals in the UK is approximately
$8.23 million, while for Africa it is $8.10 million. The independent samples t-test yields a
t-statistic of 0.37 and a p-value of 0.71. Since the p-value is much greater than 0.05, we
fail to reject the null hypothesis. There is no statistically significant difference between
the average size of a deal in the UK and in Africa.
3. Correlation Analysis
Correlation measures the strength and direction of the linear relationship between two
continuous variables.
Pair 1: Relative Strength vs. Profit %
This test determines if there is a linear relationship between a product's perceived strength
and its profit margin.
● Variables: Relative Strength in the segment and Profit %.
● Hypotheses:
○ Null Hypothesis (H0): There is no linear correlation between a product's relative
strength and the profit percentage of a deal.
H0: r=0
○ Alternate Hypothesis (Ha): There is a linear correlation between a product's relative
strength and the profit percentage of a deal.
Ha: r≠0
● Analysis: The correlation coefficient is approximately -0.016. The p-value for this
correlation is 0.615.
○ Conclusion: Since the p-value (0.615) is greater than 0.05, we fail to reject the null
hypothesis. There is no statistically significant linear relationship between the relative
strength of a product and its profit percentage.
Pair 2: Profit of Customer vs. Sales Value
This analysis checks if customers with higher profits engage in higher-value deals.
● Variables: Profit of Customer in Million and Sales Value in Million.
● Hypotheses:
○ Null Hypothesis (H0): There is no linear correlation between the customer's profit and
the sales value of the deal.
H0: r=0
○ Alternate Hypothesis (Ha): There is a linear correlation between the customer's profit
and the sales value of the deal.
Ha: r≠0
● Analysis: The correlation coefficient is approximately -0.014. The p-value is 0.655.
○ Conclusion: The p-value (0.655) is much larger than 0.05, so we fail to reject the null
hypothesis. There is no statistically significant linear relationship between the profit
of a customer and the value of the sales deal.
