Which are common effect size metrics?

• A. Cohen’s d and odds ratio.
• B. P-value and confidence interval.
• C. Sample size and power.
• D. R-squared and F-statistic.

Answer: (C)

Effect size is about how large the observed effect is, independent of sample size, so you can judge practical significance. Classic examples that quantify magnitude across different kinds of data include Cohen’s d, which standardizes the difference between two groups, and the odds ratio, which compares the odds of an outcome between groups. These metrics provide a direct sense of how big the effect is and are widely used for comparison across studies.

P-values and confidence intervals focus on significance and precision rather than the magnitude itself, so they aren’t effect size metrics by themselves. Sample size and power pertain to how study design influences the ability to detect an effect, not to the magnitude of the effect. While R-squared relates to explained variance in regression and can reflect how strongly a model accounts for data, the F-statistic is a test statistic for overall model fit rather than a direct measure of effect size, so they don’t form a standard, single set of effect size metrics.