statistical-analysis

To choose the right statistical test, evaluate your data type, sample relationship, and distribution assumptions. This skill recommends appropriate tests for group comparisons and regression by matching your research design characteristics to suitable hypothesis testing methods.

Calculating effect sizes like Cohen's d, partial eta squared, or R-squared in Python involves applying specific formulas to your summary statistics. This skill provides Python execution examples and computational logic for effect size calculations across various statistical tests.

For non-normal data distributions, you should use non-parametric statistical tests instead of parametric ones. This skill selects appropriate tests by analyzing whether your data meets normality and variance homogeneity assumptions before recommending specific comparison or regression methods.

Checking normality and variance homogeneity assumptions involves running specific preliminary tests on your dataset. This skill provides example Python execution code for common assumption checks to validate your data before proceeding with the main statistical analysis.

You can generate Python code for logistic regression analysis with APA formatted results by providing your research design and summary statistics. This skill covers linear and logistic regression scenarios, supplying runnable code and publication-ready result text.