Module 06 Activity

Scenario

Compare groups with the method the design and the data actually support.

What you build

A comparison with its assumptions checked and its power stated.

Steps

1. Decide whether the comparison is one-sample, two-sample, paired, or across three or more groups, and justify it from the design.
2. Pass equal_var=False, and report both group SDs and both sample sizes.
3. For paired data use ttest_rel and report the between-unit SD and the within-unit change SD.
4. For proportions report the absolute difference with its interval and the relative change alongside.
5. For categorical data report chi2_contingency with expected counts and standardised residuals, and switch to fisher_exact when expected counts fall below about 5.
6. For three or more groups follow f_oneway with pairwise_tukeyhsd, never with unadjusted pairwise tests.

Evidence to hand in

• The design justification for the test chosen.
• Both group SDs and sample sizes.
• The two SDs for any paired analysis.
• The absolute and relative differences for any proportion.
• The chi-square output with expected counts and residuals.
• The detectable effect size behind any null result.

Review checklist

• equal_var=False is used for every two-sample comparison.
• Paired data is analysed with ttest_rel.
• Chi-square is reported with residuals, and expected counts were checked.
• Pairwise comparisons after ANOVA are adjusted.
• Every null result is accompanied by what the study could have detected.

Mark complete