Statistical Programs |
College of Agriculture and Life Sciences |
University of Idaho |
Seminar Announcement |
"Applied Statistics in Agriculture" |
An Example from Population Genetics Where the Parametric Bootstrap Fails
Presented By |
Dr. Paul Joyce |
Deptartment of Mathematics University of Idaho |
Tuesday, December 2 3:30 P. M. Ag. Science 62 |
The stationary distributions of allele frequencies under a variety of common population genetics models called Wright-Fisher k-allele models with selection are well studied. However, the statistical properties of maximum likelihood estimates of parameters under these models are not well understood. Under each of these models there is a point in data space which carries the strongest possible signal for selection, yet, at this point, the maximum likelihood estimate for selection intensity does not exist. This result remains valid even if all other parameters in the model are assumed to be known. We will show that this singularity in data space can cause the parametric bootstrap to produces inaccurate and unreliable error estimates of the selection intensity . We describe two alternative methods to build interval estimates for the selection intensity. |
Return to Seminar Listing. |