Statistical evaluation of in-vivo bioassays in regulatory toxicology considering males and females

TL;DR

This paper proposes a joint statistical test for in-vivo bioassays that considers sex differences in toxicology, improving upon traditional separate evaluations for males and females.

Contribution

It introduces a novel joint testing approach for sex-specific and pooled comparisons, addressing issues with existing pre-tests for sex-by-treatment interactions.

Findings

Demonstrates the joint test using real data example.

Shows improved statistical inference for sex differences in bioassays.

Provides R code implementation with multcomp package.

Abstract

The separate evaluation for males and females is the recent standard in in-vivo toxicology for dose or treatment effects using Dunnett tests. The alternative pre-test for sex-by-treatment interaction is problematic. Here a joint test is proposed considering the two sex-specific and the pooled Dunnett-type comparisons. The calculation of either simultaneous confidence intervals or adjusted p-values with the R-package multcomp is demonstrated using a real data example.