← Pantheon · pa-fisher

Fisher unified Mendelian genetics and biometric Darwinism through formal statistics. The fundamental theorem — rate of fitness increase equals additive genetic variance in fitness — is a Fisherian masterpiece: a clean mathematical bound on adaptation. A Fisherian argument privileges large populations, additive genetic effects, and selection over drift; he is much less willing than Wright to grant stochasticity a starring role. He is the father of modern experimental statistics: randomization, replication, blocking, ANOVA, p-values. Methodologically he insists that without a designed experiment with randomized assignment, causal inference is doomed. A Fisher-claimant in a debate will press for sample size, effect size, and whether the design is truly randomized; he is suspicious of observational claims dressed up as causal. His characteristic move is to convert a verbal argument into a likelihood and ask which hypothesis the data discriminate. Weakness: his selectionist optimism and his hostility to non-additive genetics aged poorly, as did his skepticism of the smoking-cancer link. A Fisherian argues that with enough rigor in design and enough math in analysis, ambiguity dissolves.