Contingency table analysis with mosaic plots Chi-square, Fisher exact, McNemar, proportion difference and ratio tests, odds ratios with multiple CI methods, and mosaic plots with residual colouring — for independent and related tables.

Categorical data analysis that most packages neglect

When the data is categorical — pass/fail, treated/untreated, exposed/unexposed — you need tests designed for proportions, not means. And knowing that two variables are associated is rarely enough. You need to know where the association is strongest, how large the effect is, and whether the confidence interval on the risk difference or odds ratio is precise enough to act on.

Most packages offer a χ² test and stop there. No mosaic plots to see the pattern. No risk difference or odds ratio with proper score-based confidence intervals. No distinction between independent and related tables. No McNemar test for before-and-after designs. The categorical analysis is an afterthought — and the results reflect it.

This software is really easy to use. I’ve tried different statistical packages (e.g. SPSS, Minitab) and none are as easy or intuitive and the fact it is an add in to Excel is also very handy. The statistical guides are also really useful.

What’s included

Test for independence and see where the association lies

Pearson χ² and likelihood ratio G² tests tell you whether two categorical variables are associated. The mosaic plot shows you where — each tile’s area represents the proportion, and colouring by Pearson residual highlights which cells depart most from what independence would predict. Grouped and stacked frequency plots show conditional proportions directly.

Estimate the size of the effect in 2×2 tables

A significant χ² test doesn’t tell you how large the effect is. Proportion difference (risk difference), proportion ratio (risk ratio), and odds ratio each answer a different question — absolute difference, relative risk, or odds. Each with score-based confidence intervals that perform well even with small samples or proportions near 0 or 1.

Handle before-and-after designs with related tables

When the same subjects are measured twice — before and after treatment, two raters classifying the same cases — the observations are paired and the standard χ² test doesn’t apply. McNemar’s exact test for marginal homogeneity, proportion difference with Tango score CI, and odds ratio with exact or Wilson score CI handle the dependent structure correctly.

Example analyses

See contingency table results in detail — independence tests, mosaic plots, proportion tests, and effect sizes with CIs.

Independent table — χ² and mosaic plot
Hair–eye colour association, 4×4 table. 592 observations. Grouped frequency bar plot, Pearson χ² test for independence, mosaic plot coloured by Pearson residual.
Related table — McNemar test
Before/after intervention, 2×2 related table. 14 paired observations. Grouped frequency bar plot, McNemar test for marginal homogeneity, proportion difference with Tango score 95% CI.

Part of the Standard edition

Contingency table analysis is one part of a complete statistical analysis toolkit. The Standard edition also includes ANOVA and ANCOVA, simple and multiple regression, logistic regression, PCA and factor analysis, descriptive statistics, hypothesis testing, and correlation. See everything in the Standard edition →

Validated, reliable, trusted for over 30 years

NIST-validated calculations Every statistic tested against NIST Standard Reference Datasets, published datasets and thousands of internal test-cases. No reliance on Excel's shaky built-in functions. See how we develop and validate Analyse-it →
Data stays on your PC No cloud processing, no uploads, no third-party access. Your data never leaves your computer — essential when working with sensitive, confidential, or patient-identifiable data.
Standard Excel workbooks Analyses are ordinary Excel workbooks that you can share with colleagues, archive for audit, and open on any machine with Excel — no Analyse-it licence required.
No formulas to break Results contain no formulas, so they can't be accidentally edited or corrupted. The results you reported will be exactly what you find when you reopen the workbook.

Technical details

General r×c tables

  • Contingency table
  • Grouped frequency plot
  • Stacked frequency plot
  • Pearson χ² test for independence / equality of proportions
  • Likelihood ratio G² test for independence
  • Mosaic plot coloured by category or Pearson residual

2×2 independent tables

  • Fisher exact test for independence
  • Score Z test for difference between proportions
  • Proportion difference (risk difference) with Miettinen-Nurminen score, Newcombe score, or Tango score CI
  • Proportion ratio (risk ratio) with Miettinen-Nurminen score or Newcombe CI
  • Odds ratio with hypergeometric exact or Miettinen-Nurminen score CI

2×2 related tables

  • McNemar-Mosteller exact test for symmetry / marginal homogeneity
  • Score Z test for difference between proportions
  • Proportion difference with Newcombe score or Tango score CI
  • Odds ratio with binomial exact or Wilson score CI