Logistic Regression Analysis of Binary Traits Using Sib-Pairs Data

• Main Authors: Yu-Chieh Huang, 黃郁潔
• Other Authors: John Jen Tai
• Format: Others
• Language: zh-TW
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/16489330134261433125

碩士 === 輔仁大學 === 應用統計學研究所 === 93 === In genetics, it is not an easy work to solve the problems about QTL (quantitative trait locus) mapping. Haseman and Elston (1972) proposed a method for detecting a relationship of linkage between QTL and maker gene locus by using sib-pairs data and linear relationship between the expectation proportion of the squared trait difference (SQD) of sibs and the estimated proportion of alleles shared identical by descent (i.b.d.) at the marker locus. After testing, if the slope was significant negative, there had a meaning showed the higher of the i.b.d. scores, the closer of trait values of the sibs. And we can also find out if there existed a kind of relationship of linkage between QTL and maker gene locus. In this research, we proposed to use a logistic regression method and the rationale of Haseman-Elston method to perform binary trait loci mapping. From our simulation results, it is found that the method proposed here has best power performance under multiplicative model, and the worse power performance under recessive model. The powers under addictive and dominant models are in the second and third places.