The poolr package contains functions for pooling/combining the results (i.e., \(p\)-values) from (dependent) hypothesis tests. Included are Fisher's method, Stouffer's method, the inverse chi-square method, the Bonferroni method, Tippett's method, and the binomial test. Each method can be adjusted based on an estimate of the effective number of tests or using empirically-derived null distribution using pseudo replicates. For Fisher's, Stouffer's, and the inverse chi-square method, direct generalizations based on multivariate theory are also available (leading to Brown's method, Strube's method, and the generalized inverse chi-square method). For more details, see:

  • fisher: for Fisher's method (and Brown's method)

  • stouffer: for Stouffer's method (and Strube's method)

  • invchisq: for the inverse chi-square method

  • bonferroni: for the Bonferroni method

  • tippett: for Tippett's method

  • binomtest: for the binomial test

Note that you can also read the documentation of the package online at https://ozancinar.github.io/poolr/ (where it is nicely formatted and the output from all examples is provided).

Author

Ozan Cinar ozancinar86@gmail.com
Wolfgang Viechtbauer wvb@wvbauer.com

References

Brown, M. B. (1975). 400: A method for combining non-independent, one-sided tests of significance. Biometrics, 31(4), 987–992.

Cinar, O. & Viechtbauer, W. (2022). The poolr package for combining independent and dependent p values. Journal of Statistical Software, 101(1), 1–42. https://doi.org/10.18637/jss.v101.i01

Fisher, R. A. (1932). Statistical Methods for Research Workers (4th ed.). Edinburgh: Oliver and Boyd.

Lancaster, H. O. (1961). The combination of probabilities: An application of orthonormal functions. Australian Journal of Statistics, 3(1), 20–33.

Strube, M. J. (1985). Combining and comparing significance levels from nonindependent hypothesis tests. Psychological Bulletin, 97(2), 334–341.

Tippett, L. H. C. (1931). Methods of Statistics. London: Williams Norgate.

Wilkinson, B. (1951). A statistical consideration in psychological research. Psychological Bulletin, 48(2), 156–158.