Differential analysis & tests / Compact-letter bar chart
Your data stays in your browser: files are read and processed on your device, never uploaded to any server, and cleared when you close the page. Free, no sign-in.
Bars show group means with SD, SE or 95% CI error bars. Letters come from the multiple comparison: groups sharing a letter do not differ significantly, groups with no letter in common do (at the α you set).
Letters follow group means (Tukey) or medians (Dunn) from highest to lowest, so “a” marks the highest group; a group can carry several letters (e.g. “ab”), meaning it does not differ from either the “a” or the “b” groups.
ANOVA + Tukey HSD suits roughly normal data with similar variances; for skewed data or outliers choose Kruskal–Wallis + Dunn (P values adjusted with the method you choose).
If you map a second-factor column (e.g. variety or time point), groups are compared and lettered separately within each of its levels; letters are not comparable across levels.
Tukey (1949) Biometrics 5:99 (Tukey–Kramer for unequal n; P values match scipy.stats.tukey_hsd); Dunn (1964) Technometrics 6:241 (matches scikit-posthocs posthoc_dunn); compact letters: Piepho (2004) J Comput Graph Stat 13:456.
Up to 100,000 rows; at most 26 groups per comparison are recommended.
Send us your data and research question and you will receive a written plan within 1 working day: analysis steps, parameter rationale, deliverables and timeline. Quoted per project.