The effect of sampling error and measurement error and its correlation on the estimation of multi-locus fixed-bin VNTR RFLP genotype probabilities.

Bootstrapping was used to examine the effect of sampling error and measurement error and its correlation on fixed-bin genotype probabilities. Bootstrap confidence intervals (Cls) were made relative to the point estimate using the log of the inverse of the probabilities. From databases of 200-250 genotypes, sampling error alone yielded median relative 95% CIs of from one order of magnitude out of five for one locus to one out of ten for four loci. Measurement error of the test genotype fragments increased the latter to about one order of magnitude out of eight. Database measurement error and its correlation had only a slight effect on multi-locus probability uncertainty. Together, these uncertainties are several orders of magnitude greater than error due to population substructuring of a race by its major component ethnic groups.