dc.contributor.advisor Liu, Jun dc.contributor.author Jiang, Bo dc.date.accessioned 2013-09-27T21:00:36Z dc.date.issued 2013-09-27 dc.date.submitted 2013 dc.identifier.citation Jiang, Bo. 2013. Partition Models for Variable Selection and Interaction Detection. Doctoral dissertation, Harvard University. en_US dc.identifier.other http://dissertations.umi.com/gsas.harvard:10911 en dc.identifier.uri http://nrs.harvard.edu/urn-3:HUL.InstRepos:11124828 dc.description.abstract Variable selection methods play important roles in modeling high-dimensional data and are key to data-driven scientific discoveries. In this thesis, we consider the problem of variable selection with interaction detection. Instead of building a predictive model of the response given combinations of predictors, we start by modeling the conditional distribution of predictors given partitions based on responses. We use this inverse modeling perspective as motivation to propose a stepwise procedure for effectively detecting interaction with few assumptions on parametric form. The proposed procedure is able to detect pairwise interactions among p predictors with a computational time of $O(p)$ instead of $O(p^2)$ under moderate conditions. We establish consistency of the proposed procedure in variable selection under a diverging number of predictors and sample size. We demonstrate its excellent empirical performance in comparison with some existing methods through simulation studies as well as real data examples. Next, we combine the forward and inverse modeling perspectives under the Bayesian framework to detect pleiotropic and epistatic effects in effects in expression quantitative loci (eQTLs) studies. We augment the Bayesian partition model proposed by Zhang et al. (2010) to capture complex dependence structure among gene expression and genetic markers. In particular, we propose a sequential partition prior to model the asymmetric roles played by the response and the predictors, and we develop an efficient dynamic programming algorithm for sampling latent individual partitions. The augmented partition model significantly improves the power in detecting eQTLs compared to previous methods in both simulations and real data examples pertaining to yeast. Finally, we study the application of Bayesian partition models in the unsupervised learning of transcription factor (TF) families based on protein binding microarray (PBM). The problem of TF subclass identification can be viewed as the clustering of TFs with variable selection on their binding DNA sequences. Our model provides simultaneous identification of TF families and their shared sequence preferences, as well as DNA sequences bound preferentially by individual members of TF families. Our analysis may aid in deciphering cis regulatory codes and determinants of protein-DNA binding specificity. en_US dc.description.sponsorship Statistics en_US dc.language.iso en_US en_US dash.license LAA dc.subject Statistics en_US dc.subject Hierarchical models en_US dc.subject Inverse models en_US dc.subject Quantitative trait loci en_US dc.subject Sliced inverse regression en_US dc.subject Sure independence screening en_US dc.subject Transcriptional regulation en_US dc.title Partition Models for Variable Selection and Interaction Detection en_US dc.type Thesis or Dissertation en_US dash.depositing.author Jiang, Bo dc.date.available 2013-09-27T21:00:36Z thesis.degree.date 2013 en_US thesis.degree.discipline Statistics en_US thesis.degree.grantor Harvard University en_US thesis.degree.level doctoral en_US thesis.degree.name Ph.D. en_US dc.contributor.committeeMember Liu, Jun en_US dc.contributor.committeeMember Bulyk, Martha en_US dc.contributor.committeeMember Blitzstein, Joseph en_US dash.contributor.affiliated Jiang, Bo
﻿