Combine p-values using Fisher's Method

Aggregates a vector of p-values using Fisher's method, which tests the union null hypothesis that all component tests are null. This method is powerful when multiple weak signals are present across independent or weakly correlated tests.

Usage

combine_fisher(pvals)

Arguments

pvals

A numeric vector of p-values (typically for the same predictor across models or effects).

Value

A scalar: the Fisher-combined p-value.

Details

The test statistic is \(T = -2 \sum \log(p_i)\), which follows a chi-squared distribution with \(2k\) degrees of freedom under the null, where \(k\) is the number of p-values.

Examples

if (FALSE) { # \dontrun{
p <- c(0.01, 0.2, 0.04)
combine_fisher(p)
} # }