Exploring the HDL likelihood surface

Publisher Website
Google Scholar
Abstract
Using random initial parameter estimates, three segregation analysis models of the inheritance of HDL, in the Berkeley GAW8 data set were maximized 5000 times each. Initial parameter estimates were assumed to be uniformly distributed on intervals formed by parameter boundaries. The three models were unrestricted, environmental, and Mendelian regressive type A models. Likelihood ratio tests of the global maxima rejected the Mendelian model and accepted the environmental model. However, tests using local maxima accepted the Mendelian model and both rejected and accepted the environmental model. Patterns among the initial parameter estimates of convergent runs were examined to develop empirical rules to increase the frequency of convergence. These rules were tested using data on apo AI in the Berkeley GAWS data set.

This publication has 1 reference indexed in Scilit: