Welcome to Statif
Browsing as guest
Tests & Formulas
Every method Statif runs — with its formula and a published source. Statif computes these on your real data; nothing is invented.
Descriptive · 2
Descriptive Statistics
Summarise the central tendency, dispersion and shape of each numeric variable.
Frequency Tables
Count how observations distribute across the categories of a variable.
Association · 5
Pearson Correlation
Measure the strength and direction of a linear relationship between two numeric variables.
Spearman's Rank Correlation (ρ)
Measure a monotonic relationship using ranks, robust to outliers and non-normality.
Kendall's tau-b (τ)
Rank correlation based on concordant vs discordant pairs; handles ties.
Partial Correlation
Correlation between two variables while controlling for a third.
Correlation Matrix
All pairwise correlations among numeric variables, visualised as a heatmap.
Assumptions · 4
Shapiro–Wilk Test
Test whether a variable is normally distributed.
Jarque–Bera Test
Test normality using sample skewness and kurtosis.
Levene's Test (median-centred)
Test equality of variances across groups (homogeneity of variance).
Bartlett's Test
Test equality of variances assuming normal data.
Mean & Rank Tests · 10
One-Sample t-Test
Compare a sample mean to a known/hypothesised value.
Independent-Samples t-Test
Compare the means of two independent groups (equal variances).
Welch's t-Test
Compare two group means without assuming equal variances.
Paired-Samples t-Test
Compare two related measurements (e.g. before vs after).
One-Way ANOVA
Compare means across three or more independent groups.
Welch's ANOVA
Compare 3+ group means without assuming equal variances.
Mann–Whitney U Test
Non-parametric comparison of two independent groups.
Wilcoxon Signed-Rank Test
Non-parametric comparison of two related samples.
Kruskal–Wallis H Test
Non-parametric comparison of three or more independent groups.
Sign Test
Test the median difference of paired data using only signs.
Categorical · 5
Chi-Square Goodness of Fit
Test whether observed category counts match expected proportions.
Chi-Square Test of Independence
Test whether two categorical variables are associated.
Fisher's Exact Test
Exact test of association in a 2×2 table.
McNemar's Test
Test change in paired binary outcomes.
Cochran's Q Test
Test differences in a binary outcome across 3+ repeated measures.
Models · 2
Linear Regression (OLS)
Model a numeric outcome as a linear function of predictors.
Binary Logistic Regression
Model the probability of a binary outcome from predictors.
Reliability & Agreement · 2
Cronbach's Alpha
Estimate internal-consistency reliability of a set of items/scale.
Cohen's Kappa
Measure inter-rater agreement for categorical ratings, correcting for chance.
Effect Sizes · 1
Effect Sizes
Quantify the magnitude of an effect, independent of sample size.
Multiple Testing · 3
Bonferroni Correction
Control the family-wise error rate across many tests (conservative).
Holm–Bonferroni Correction
Control family-wise error rate with more power than Bonferroni.
Benjamini–Hochberg (FDR)
Control the false discovery rate — powerful for many tests.