Testing the fit of the logistic model for matched case-control studies
學年 101
學期 1
出版(發表)日期 2013-01-01
作品名稱 Testing the fit of the logistic model for matched case-control studies
作品名稱(其他語言)
著者 Chen, Li-ching; Wang, Jiun-yi
單位 淡江大學統計學系
出版者 Amsterdam: Elsevier BV
著錄名稱、卷期、頁數 Computational Statistics & Data Analysis 57(1), pp.309–319
摘要 With numerous statistical packages being easily available to conduct the logistic regression analysis, assessment for the goodness-of-fit in the logistic case-control studies becomes more important in practice. While various methods for model checking in conventional case-control studies have been proposed in the literature, methods for checking model adequacy with matched case-control data get relatively less attention. In this study, we propose an omnibus goodness-of-fit test to assess adequacy of the conditional logistic model for matched case-control data. The proposed test can be either constructed based on the discrepancy between two moment estimations or derived to be a score-type test under a general random-effects model. Computation of the proposed test is quite simple in which it does not need to partition the covariate space or to estimate p-value of the test via simulations. The asymptotic null distribution and power calculation of the test are derived under a sequence of alternatives. Empirical type I error rates and powers of the test are performed by simulation studies. An example has been used to illustrate the proposed method as well.
關鍵字 General random effects model; Goodness-of-fit; Matched case-control data; Moment estimation; Logistic model
語言 en_US
ISSN 0167-9473
期刊性質 國外
收錄於 SCI
產學合作
通訊作者 Wang, Jiun-yi
審稿制度
國別 NLD
公開徵稿
出版型式 紙本
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/78353 )

機構典藏連結