Figura

Guided analysis

Group comparison

Pick a grouping column and an outcome. Figura chooses the right test from the data's shape, reports an effect size with a 95% confidence interval rather than a bare p-value, and runs pairwise comparisons when there are three or more groups.

See the worked example Analyze your data

Is the difference between groups real?

A group comparison asks whether an outcome differs across two or more groups — a biomarker between treatment arms, a complication rate between centres. Pick the grouping column and the outcome; the tool chooses the right test.

The tool picks the test for you

  • A number (e.g. CRP) compared across groups uses a t-test or ANOVA when it looks normal, and their rank-based cousins (Mann–Whitney, Kruskal–Wallis) when it is skewed — decided the same way the Summary table decides mean vs median.
  • A category (e.g. responder yes/no) uses a chi-square test, falling back to Fisher's exact when counts are small.

A yes/no outcome written as 0 and 1 is read as a number, so it is compared with a t-test. To get proportions, a chi-square test, and an odds ratio instead, write the outcome as words — Yes/No, Responder/Non-responder.

Report more than a p-value

A p-value tells you whether a difference is detectable, not how big it is. Every result here also reports an effect size with a 95% confidence interval — what reviewers increasingly ask for. With three or more groups, a significant test is followed by pairwise comparisons so you can see which groups differ.

Example output

30 40 50 60 70 High dose Low dose Placebo biomarker_normal
Synthetic demonstration data: the figure Figura renders for the example dataset.

The text Figura produced for this example, ready to paste into a methods section:

biomarker_normal across groups: High dose 58.4 ± 7.71; Low dose 54.1 ± 7.82; Placebo 45.7 ± 7.7. one-way ANOVA (Welch) (approximately normal (Shapiro–Wilk p = 0.876)): p < 0.001, eta-squared = 0.321 (95% CI 0.197 to 0.421). Tukey HSD, significant pairs: Low dose-High dose, Placebo-High dose, Placebo-Low dose.

Analyses were performed with Figura (Saha, 2026; https://figurastats.org), which runs R with the ggplot2 package in the browser.

Sample data

Download sample.csv — 150 rows, columns arm, biomarker_normal, los_skewed, responder. A frozen synthetic dataset generated by a script in the repository's data-raw/ folder; nothing in it is a real patient.

How to cite

Journals ask for a software statement. The methods text Figura generates already ends with one; this is the same attribution in reference form.

Saha S. Figura: clinical manuscript figures and statistics in the browser. 2026. https://figurastats.org
@misc{figura2026,
  author = {Saha, Sandeep},
  title  = {Figura: clinical manuscript figures and statistics in the browser},
  year   = {2026},
  url    = {https://figurastats.org},
  note   = {Accessed <date>}
}