Premium
A Comparative Statistical Analysis of Genetic Distances. II–Confidence Intervals and Tests of Comparison
Author(s) -
Katz Mariano
Publication year - 1989
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710310816
Subject(s) - statistics , estimator , confidence interval , mathematics , monte carlo method , statistical hypothesis testing , standard error , null hypothesis
We present methods for constructing the confidence intervals of the estimations of absolute genetic distance and Nei's minimum and standard genetic distances. Two different estimators of the standard distance are considered: jack‐knife and corrected. A Monte‐Carlo simulation analysis permitted to choose the best adapted confidence interval type for each distance estimator and for each size of the samples of loci and of gametes, taking into account the magnitude of the estimation value. Simulated true confidence levels showed that the best results are obtained using abolute genetic distance. We also give rules for testing the significance of the difference of two distance estimations. Monte‐Carlo simulations were performed in order to obtain the distributions of the difference of two distance estimations under the null hypothesis and consequently the true type I errors of tests. Test powers, obtained by simulation under the alternative hypothesis, also showed the superiority of absolute genetic distance.