Date of Award


Degree Type


Degree Name

Master of Science (MS)


Mathematics and Statistics

Committee Chair(s)

Chris Corcoran


Chris Corcoran


John Stevens


Maria Norton


Family-based association tests are used to identify genes that increase the risk of developing a disease, while controlling for spurious associations caused by population structure. The exact family-based association test, exact FBAT, is a unified approach which can be app lied to tests of different genetic models, sampling designs, null hypotheses , and missing parental information.

The purpose of this report is to compare the power of the exact FBAT with two other tests, exact conditional logistic regression (CLR) and the exact trend test for clustered data (QEM). Pedigrees of sibships were simulated based upon a variety of different parameters, and then the test statistic was calculated for each. Examining the power for each test, we find that QE 1 is clearly the most powerful test among the three in detecting linkage among data from sampled sibships. The difference in power among exact FBAT and exact CLR is small, with exact CLR demonstrating a slight advantage over exact FBAT. While the relative differences in power is substantial for small sample size8, the gaps shrink as the number of families increases.