CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: Model checking for logistic models when the number of parameters tends to infinity Authors:  Xiumin Li - Qingdao University (China)
Feifei Chen - Beijing Normal University (China) [presenting]
Hua Liang - George Washington University (United States)
David Ruppert - Cornell University (United States)
Abstract: A projection-based test is proposed to check logistic regression models when the dimension of the covariate vector may be divergent. The proposed test achieves a reduction in dimension, and the proposed method behaves as if only a single covariate is present. The test is shown to be consistent and can detect root-n local alternatives. We derive the asymptotic distribution of the proposed test under the null hypothesis and establish the test's asymptotic behavior under the local and global alternatives. The numerical performance is remarkably attractive compared to the existing methods. Real examples are presented for illustration.