AWS Certified Machine Learning – SpecialtyExploratory Data AnalysisMedium
A retail company is analyzing sales data from their e-commerce platform. They want to determine if a recent website redesign (implemented last month) had a significant impact on the average daily sales. They have daily sales data for the month before the redesign and the month after the redesign. The data is known to be approximately normally distributed, and the two months represent independent samples. Which hypothesis test should they use?
- APaired sample t-test, as it compares means of related samples.
- BChi-squared test, to assess the association between categorical variables.
- CIndependent samples t-test, to compare means of two independent groups.
- DANOVA, to compare means of more than two groups.
Show answer & explanationAnswer & explanation
Correct answer: C. Independent samples t-test, to compare means of two independent groups.
An independent samples t-test is appropriate for comparing the means of two distinct, unrelated groups (sales before redesign vs. sales after redesign) when the data is approximately normally distributed.
Why the other options are wrong
- A. Incorrect. A paired sample t-test is used when the two samples are related (e.g., before and after measurements on the same subjects), which is not the case here as the daily sales are from different, independent days/periods.
- B. Incorrect. A Chi-squared test is used for categorical variables to assess association, not for comparing means of continuous sales data.
- D. Incorrect. ANOVA is used to compare means of three or more groups, not just two.
Independent Samples T-test
A statistical hypothesis test used to determine if there is a significant difference between the means of two independent groups.
- Compares means of two unrelated samples.
- Assumes normality and equal variances (or uses Welch's t-test if variances are unequal).
- Null hypothesis: means are equal.
Memory trick: T-test for two, ANOVA for many groups to view.