Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Penalized Score Test for High Dimensional Logistic Regression
Document related concepts
Algorithm characterizations wikipedia , lookup
Factorization of polynomials over finite fields wikipedia , lookup
Predictive analytics wikipedia , lookup
Generalized linear model wikipedia , lookup
Smith–Waterman algorithm wikipedia , lookup
Psychometrics wikipedia , lookup
Simplex algorithm wikipedia , lookup
Expectation–maximization algorithm wikipedia , lookup
K-nearest neighbors algorithm wikipedia , lookup
Transcript
Department of Statistics MASTER’S THESIS PRESENTATION MING YU Department of Statistics The University of Chicago Penalized Score Test for High Dimensional Logistic Regression TUESDAY, February 16, 2016, at 9:00 AM Eckhart 110, 5734 S. University Avenue ABSTRACT We deal with inference problem for high dimensional logistic regression. The main idea is to give penalized estimator by adding penalty to negative log likelihood function which penalizes all variables except the one we are interested in. It shows that this penalized estimator is a compromise between the multiple regression and simple regression. We then use the algorithm called penalized score test to give valid test for the variable of interest with asymptotic designed Type I error. We check our algorithm on both simulated and real datasets. _______________________________ For information about building access for persons with disabilities, please contact Laura Rigazzi at 773.702-0541 or send an email to [email protected] If you wish to subscribe to our email list, please visit the following web site: https://lists.uchicago.edu/web/arc/statseminars.
