Analyses of gene frequencies

Abstract

Models of variance components and their intraclass correlational equivalences are developed for genes falling into various categories of subdivisions within a population. Estimable functions are elaborated demonstrating that intraclass correlations can be estimated only relative to that for the least related genes in the informational system. The effects of different types of subdivisions-and of ignoring them-on the parameters are demonstrated. Small sample estimators are formulated for all of the parameters by three different methods, including both a weighted and an unweighted method of analysis of the variation among subpopulations. How estimators change with assumptions about the parameters is illustrated. Various tests of hypotheses are outlined in chi(2) and F-test terminology. Discussed are factors which may affect the correlations and the manner in which their effects are manifest, hopefully in clarification of some of the misconceptions that have arisen in this connection.