Implement Statistical Hypothesis Tests
Description
This MR includes the project's statistical analysis capabilities by introducing several new statistical test functions:
Statistical Tests Introduced
-
Mann-Whitney U Test
- A non-parametric test used to assess whether two independent samples come from the same distribution.
- Useful when data does not meet the assumptions required for the t-test.
-
One-Way ANOVA
- A parametric test comparing the means of three or more groups to determine if there is a statistically significant difference between them.
- Widely used in experiments with multiple group comparisons.
-
Kruskal-Wallis Test
- A non-parametric test for comparing more than two groups to determine whether they come from the same distribution.
- Serves as an alternative to the One-Way ANOVA for non-normally distributed data.
-
Log-Rank Test
- A statistical test used to compare the survival distributions of two groups.
- Common in medical research and clinical trials for time-to-event analysis.
-
Independent Student t-Test (New)
- A parametric test comparing the means of two independent groups to determine if they are significantly different.
-
One-Sample Student t-Test (New)
- A parametric test used to compare the mean of a single sample to a known value or population mean.
These functions empower researchers and analysts with tools for parametric, non-parametric, and survival analysis, making the toolkit robust across a wide range of statistical scenarios.
Conformity
-
Changelog Entry: Update the Changelog with the new additions. -
Unit Tests: Write and validate unit tests for all new functions. -
INSTALL Update: Update installation instructions if there are new dependencies or configurations. -
Downport: Ensure backward compatibility or provide clear documentation for any incompatibilities. -
Bug Fixes: Specify any bugs fixed by this patch.
When External Dependencies Are Removed
-
Properly report and document the removal of any external dependencies.
Edited by Kuntal Bar