A method of subdividing genetic data into self-contained subsets

Authors


Summary

A method of subdividing genetic data into self-contained subsets has been described in terms of examples. The subsets are such that each of them permits a valid estimate of the parameter concerned. Hence, the discarding of one or more subsets would not affect the validity of the remaining data. The detailed statistical properties of such subsets await further investigation. There is a need to simplify the variance formulas for estimates based on partial data.

Ancillary