1---
2name: statistical-reporting
3description: Statistical test selection, assumption checking, and APA-formatted reporting. Use when analyzing experimental results or writing results sections.
4metadata:
5 source: https://skillmd.com/skills/enuno/statistical-reporting
6 category: writing
7 trigger-keywords: "statistic,hypothesis test,p-value,regression,ANOVA,t-test,effect size,confidence interval"
8 applicable-stages: "14,17"
9 priority: "3"
10 version: "1.0"
11 author: researchclaw
12 references: "adapted from K-Dense-AI/claude-scientific-skills"
13---
14
15## Statistical Reporting Best Practice
16
17### Test Selection Quick Reference
181. **Comparing two groups (independent, normal)**: Independent t-test
192. **Comparing two groups (independent, non-normal)**: Mann-Whitney U test
203. **Comparing two groups (paired, normal)**: Paired t-test
214. **Comparing two groups (paired, non-normal)**: Wilcoxon signed-rank test
225. **Comparing 3+ groups (independent, normal)**: One-way ANOVA + post-hoc
236. **Comparing 3+ groups (non-normal)**: Kruskal-Wallis test
247. **Relationship between continuous variables**: Pearson or Spearman correlation
258. **Categorical outcomes**: Chi-square or Fisher's exact test
269. **Predicting continuous outcome**: Linear regression
2710. **Predicting binary outcome**: Logistic regression
28
29### Assumption Checking
301. **Normality**: Shapiro-Wilk test (n < 50) or visual Q-Q plots
312. **Homogeneity of variance**: Levene's test before t-tests and ANOVA
323. **Independence**: Verify study design ensures independent observations
334. **Linearity**: Scatter plots and residual plots for regression
345. **Multicollinearity**: VIF < 5 for multiple regression predictors
356. When assumptions are violated, use non-parametric alternatives or robust methods
36
37### APA Reporting Format
381. **t-test**: t(df) = X.XX, p = .XXX, d = X.XX
392. **ANOVA**: F(df_between, df_within) = X.XX, p = .XXX, eta-squared = .XX
403. **Correlation**: r(df) = .XX, p = .XXX [95% CI: .XX, .XX]
414. **Chi-square**: chi-square(df, N = XXX) = X.XX, p = .XXX
425. **Regression**: beta = X.XX, SE = X.XX, t = X.XX, p = .XXX
436. Always report exact p-values (not "p < .05") unless p < .001
447. Use leading zero for values that can exceed 1 (e.g., t = 0.50) but not for those bounded by 1 (e.g., p = .032, r = .45)
45
46### Effect Sizes
471. ALWAYS report effect sizes alongside p-values
482. Cohen's d for group comparisons: small = 0.2, medium = 0.5, large = 0.8
493. Eta-squared for ANOVA: small = .01, medium = .06, large = .14
504. R-squared for regression: report adjusted R-squared for multiple predictors
515. Odds ratios for logistic regression with 95% confidence intervals
526. Distinguish statistical significance from practical significance
53
54### Common Mistakes to Avoid
551. Never say "the results were not significant, therefore there is no effect"
562. Do not confuse correlation with causation in observational data
573. Apply multiple comparison corrections (Bonferroni, FDR) when running many tests
584. Report confidence intervals, not just point estimates
595. State whether tests are one-tailed or two-tailed and justify the choice