Correlated binary data analysis using robust likelihood
碩士 === 國立中央大學 === 統計研究所 === 97 === Correlated data are commonly encountered in many fields. The correlation may come from the genetic heredity, familial aggregation, environmental heterogeneity, or repeated measures. Royall and Tsou (2003) proposed a parametric robust likelihood technique. With larg...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2009
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/62465397378121646143 |
| Summary: | 碩士 === 國立中央大學 === 統計研究所 === 97 === Correlated data are commonly encountered in many fields. The correlation may come from the genetic heredity, familial aggregation, environmental heterogeneity, or repeated measures. Royall and Tsou (2003) proposed a parametric robust likelihood technique. With large samples, the adjusted binomial likelihood is asymptotically legitimate for correlated binary data.
In this work, we use the adjustment by the binomial working model and obtain a new method for estimating the correlation between data in a cluster.
|
|---|