Which Statistical Test for Docking Scores? ANOVA, t-Tests and the Right Choice Every Time

By BioDockify Computational Research Team · October 11, 2026 · Tutorials

The complete decision guide for docking-score statistics: normality tests, paired vs independent t-tests, one-way ANOVA with Tukey, Mann-Whitney and Kruskal-Wallis, effect sizes, and the exact sentence to report - with a worked example on 6 compounds.

Read the complete article with tables, code and references on BioDockify.

Key References

• Trott, O. & Olson, A.J. AutoDock Vina. J. Comput. Chem. 31, 445-461 (2010). DOI: 10.1002/jcc.21334
• Shapiro, S.S. & Wilk, M.B. An analysis of variance test for normality. Biometrika 52, 591-611 (1965).
• Wasserstein, R.L. & Lazar, N.A. The ASA statement on p-values. Am. Stat. 70, 129-133 (2016). DOI: 10.1080/00031305.2016.1154108
• Tukey, J.W. Comparing individual means in the analysis of variance. Biometrics 5, 99-114 (1949).
• Kruskal, W.H. & Wallis, W.A. Use of ranks in one-criterion variance analysis. J. Am. Stat. Assoc. 47, 583-621 (1952).
• Cohen, J. Statistical Power Analysis for the Behavioral Sciences, 2nd ed. (1988).

Scope & Limitations

Score statistics assume independent docking runs; correlated protocols (same seed, same pose) violate independence Normality conclusions from small n (few poses) are weak - report the test but do not over-trust it