Letter to the Editor re: Millar and Broadhurst (2025): “Incorrect inference from size-selectivity studies due to widespread misuse of bootstrap confidence bands” [Fisheries Research 281, 107225]

Millar and Broadhurst (2025) claim incorrect inference from catch comparison and size selectivity studies due to misuse of bootstrap confidence bands by Type I error inflation. They applied joint (union intersection) hypothesis testing to investigate the risk of Type I error inflation and evaluate the performance of what they refer to as the “confidence bands test”. We outline our views on three debatable aspects of the study with the support of published literature both within and outside the field of fisheries research. (i) The studies that Millar and Broadhurst (2025) claimed to have misused bootstrap confidence bands for hypothesis testing do not use joint hypothesis testing. They make statistical inference based on individual and separate assessments of the magnitude of an effect and the accuracy in estimation of the effect for each length class. This approach is not subjected to Type I error inflation. Consequently, the claim of incorrect inference in Millar and Broadhurst (2025) is unjustified. (ii) To