Tools – Stat Tools

Tip: try keywords like “confidence”, “holm”, “welch”.

All

Agreement & Reliability

Corrections

Descriptive

Effect Sizes

Hypothesis Tests

Inference

Method Comparison

Planning

Selector

Which statistical test should I use?

Guided wizard to pick the right statistical test.

Selector wizard assumptions paired normality

Significance checker

Check if p ≤ alpha and get a clear decision.

Inference p-value alpha decision

t-test (Welch two-sample)

Compute Welch t-test from two groups of numbers.

Inference welch two-sample p-value df

One-way ANOVA

Compute one-way ANOVA from multiple groups.

Inference F p-value groups

Std dev & uncertainty

Compute mean, variance, sd, SE, and 95% CI of the mean.

Descriptive variance standard error CI

Confidence interval

CI for mean (t) or proportion (Wilson). Includes steps.

Inference t-based wilson margin

Sample size

Required n for mean/proportion given confidence and margin.

Planning power margin z

Multiple testing correction

Adjust p-values for multiple comparisons with step-by-step output.

Corrections bonferroni holm benjamini-hochberg FDR

Bland–Altman (method comparison)

Agreement between two measurement methods (bias + LoA).

Method Comparison bland-altman limits-of-agreement bias

Cohen’s kappa (agreement)

Inter-rater agreement beyond chance for categorical labels.

Agreement & Reliability kappa agreement inter-rater

McNemar test (paired 2×2)

Paired nominal test using discordant pairs (b,c).

Hypothesis Tests mcnemar paired 2x2

Cliff’s delta (effect size)

Non-parametric effect size based on pairwise dominance.

Effect Sizes cliffs-delta nonparametric effect-size

Vargha–Delaney A12

Probability of superiority effect size (ties=0.5).

Effect Sizes a12 vargha-delaney probability