Hidden Markov Model in Multiple Testing on Dependent Data

Add to your list(s) Download to your calendar using vCal

• Xia Wang (University of Cincinnati)
• Tuesday 06 December 2022, 14:00-15:00
• https://bham-ac-uk.zoom.us/j/85964416482?pwd=NEdPZEhZWFNYdHRYcndNczFyRWlaZz09; Meeting ID: 859 6441 6482 Passcode: 339766.

If you have a question about this talk, please contact Hong Duong.

Multiple testing on dependent data needs to handle two basic modeling elements: the choice of distributions under the null and the non-null states and the modeling of the dependence structure across observations. A Bayesian hidden Markov model is constructed to handle these two issues. The proposed Bayesian method is based on the posterior probability of the null state and exhibits the property of an optimal test procedure, which has the lowest false negative rate with the false discovery rate under control. The model has either single or mixture distributions used under the non-null state, which can be flexibly modeled by ad-hoc model selection or the nonparametric Bayesian method. The proposed method is applied to both continuous and count data. We compared the proposed method with a collection of commonly used testing procedures to show its performance under different scenarios.

This talk is part of the Data Science and Computational Statistics Seminar series.

This talk is included in these lists:

• Data Science and Computational Statistics Seminar
• School of Mathematics events
• https://bham-ac-uk.zoom.us/j/85964416482?pwd=NEdPZEhZWFNYdHRYcndNczFyRWlaZz09; Meeting ID: 859 6441 6482 Passcode: 339766

Note that ex-directory lists are not shown.