Browsing by Author "Anastasios Tsiatis, Member"
Now showing 1 - 19 of 19
- Results Per Page
- Sort Options
- Accelerated Failure Time Model for Correlated Survival Data: Efficient Estimation and Inference.(2012-04-25) Liu, Bo; Wenbin Lu, Chair; Anastasios Tsiatis, Member; Daowen Zhang, Member; Arnab Maity, Member; John Gilligan, Graduate School Representative
- Bayesian Inference about Some Geometric Aspects of Nonparametric Functions.(2018-07-23) Li, Wei; Subhashis Ghoshal, Chair; Anastasios Tsiatis, Member; Rui Song, Member; Brian Reich, Member; Carrol Adams Warren, Graduate School Representative
- Estimating Causal Treatment Effects via the Propensity Score and Estimating Survival Distributions in Clinical Trials That Follow Two-Stage Randomization Designs(2001-08-15) Lunceford, Jared Kenneth; Marie Davidian, Chair; Anastasios Tsiatis, Member; Dennis Boos, Member; Daowen Zhang, MemberEstimation of treatment effects with causalinterpretation from obervational data is complicated by the fact thatexposure to treatment is confounded with subject characteristics. Thepropensity score, the probability of exposure to treatment conditionalon covariates, is the basis for two competing classes of approachesfor adjusting for confounding: methods based on stratification ofobservations by quantiles of estimated propensity scores, and methods based on weighting individual observations by weights depending onestimated propensity scores. We review these approaches andinvestigate their relative performance.Some clinical trials follow a design in which patientsare randomized to a primary therapy upon entry followed by anotherrandomization to maintenance therapy contingent upon diseaseremission. Ideally, analysis would allow different treatmentpolicies, i.e. combinations of primary and maintenance therapy ifspecified up-front, to be compared. Standard practice is to conductseparate analyses for the primary and follow-up treatments, which doesnot address this issue directly. We propose consistent estimators ofthe survival distribution and mean survival time for each treatmentpolicy in such two-stage studies and derive large sampleproperties. The methods are demonstrated on a leukemia clinical trialdata set and through simulation.
- Estimating optimal control strategies for large scale spatio-temporal decision problems.(2017-08-10) Meyer, Nicholas James; Eric Laber, Chair; Brian Reich, Member; Marie Davidian, Member; Anastasios Tsiatis, Member; Jamian Pacifici, Graduate School Representative
- Flexible Estimation and Testing Methods for Survival Data with Application in Epidemiology and Precision Medicine.(2017-04-28) Kang, Suhyun; Wenbin Lu, Chair; Daowen Zhang, Member; Anastasios Tsiatis, Member; Rui Song, Member; Mitzi Stumpf, Graduate School Representative
- Flexible Statistical Learning Methods for Survival Data: Risk Prediction and Optimal Treatment Decision.(2013-05-03) Geng, Yuan; Hao Zhang, Co-Chair; Wenbin Lu, Co-Chair; Anastasios Tsiatis, Member; Eric Laber, Member; Gary Payne, Graduate School Representative
- General Zero-Inflated Models and Their Applications(2000-03-31) Gan, Nianci; Jye-Chyi Lu, Chair; Anastasios Tsiatis, Member; Sujit Ghosh, Member; Matthias Stallmann, MemberCount data with excess zeros are commonly seen in experiments forimproving electronics manufacturing quality, in medical researchof HIV patients with high-risk behaviors and in agricultural study of number of insects per leaf.Yip (1988) and Lambert (1992) proposed zero-inflated Poisson distribution andHeilbron (1989) used zero-altered Poisson and negative binomial distributionsto model this type of data. Li, Lu, Park, Kim, Brinkley and Peterson (1999)derived multivariate version of the zero-inflated Poisson distribution andapplied it to detect equipment problems in electronics manufacturingprocesses. Zero-inflated distributions assume that with probability 1 - p the onlypossible observation is 0, and with probability p, a random variabledescribing defect counts in the imperfect state is observed. For example, when manufacturing equipment is properlyaligned (perfect state), there may be no defects. Otherwise, defects may occuraccording to a distribution of the imperfect state. The defect counts inimperfect state could follow Poisson, negative binomial, or other distributions but most of the current researches use Poisson distribution. Although the maximum likelihood (ML) method is widely used in estimatingparameters in the zero-inflated distributions, there is no theoreticalstudy on the properties of the ML estimates.In Chapter 1, we propose a generalframework for generalized zero-inflated models (ZIM), which assume only thatthe distribution of the imperfect state has the support of the nonnegativeintegers and satisfies appropriate regularity conditions. We study the properties of the ML estimates of ZIM parameters,including their existence, uniqueness, strong consistencyand asymptotic normality under regularity conditions. By focusing on the univariate ZIM, we give detailedrigorous proofs to the lemmas and theorems stated in the thesis. Then, we study covariate effects in the univariate and multivariate zero-inflated regression models. Because the zero-inflated model involves both Bernoulli parameter p and the imperfect state parameter lambda,building the model separately does not use the information efficiently and the resulted model is more complicated than needed. This problem gets worse in the multivariate ZIM, where the number of model terms increases drastically. Our procedure selects limited important model terms to maximize the ZIM likelihood functions. In Chapter 2, we review current researches on zero-inflated Poissonmodels. Some new results on multivariate Poisson and multivariate zero-inflated Poisson distributions are given. By generalizing theresults in Lambert (1992) and Li, et al (1999), we propose a multivariatezero-inflated Poisson regression model. An example from Nortel process development research is used to illustrate the model selection procedure for the zero-inflated regression models and computational details.
- Interactive Modeling Techniques for Non-smooth Functionals in Dynamic Treatment Regimes.(2014-04-28) Linn, Kristin Ashley; Leonard Stefanski, Co-Chair; Eric Laber, Co-Chair; Marie Davidian, Member; Anastasios Tsiatis, Member; Jonathan Ocko, Graduate School Representative
- Joint Modeling of Primary Binary Outcome and Longitudinal Covariates Measured at Informative Observation Times.(2011-11-01) Yan, Song; Daowen Zhang, Chair; Wenbin Lu, Co-Chair; Marie Davidian, Member; Anastasios Tsiatis, Member; Charlotte Farin, Graduate School Representative
- List-based Interpretable Dynamic Treatment Regimes.(2016-05-04) Zhang, Yichi; Eric Laber, Co-Chair; Marie Davidian, Co-Chair; Anastasios Tsiatis, Member; Leonard Stefanski, Member; Jaime Collazo, Graduate School Representative
- On Statistical Learning for Individualized Decision Making with Complex Data.(2019-06-03) Shi, Chengchun; Wenbin Lu, Co-Chair; Rui Song, Co-Chair; Soumendra Lahiri, Member; Anastasios Tsiatis, Member; Shaina Race, Graduate School Representative
- Optimal Treatment Regimes under Constraints.(2017-12-19) Ruan, Shuping; Eric Laber, Chair; Leonard Stefanski, Member; Anastasios Tsiatis, Member; Marie Davidian, Member; Jamian Pacifici, Graduate School Representative
- Robust Learning for Optimal Treatment Strategy with Survival Data(2015-05-14) Jiang, Runchao; Wenbin Lu, Co-Chair; Rui Song, Co-Chair; Anastasios Tsiatis, Member; Marie Davidian, Member; Osman Ozaltin, Graduate School Representative
- Semiparametric Estimation and Inference for Censored Regression Models.(2011-11-10) Pang, Lei; Huixia Wang, Co-Chair; Wenbin Lu, Co-Chair; Anastasios Tsiatis, Member; Daowen Zhang, Member; Jerry Davis, Graduate School Representative
- Semiparametric Regression Methods for Longitudinal Data with Informative Observation Times and/or Dropout.(2011-06-16) Cai, Na; Wenbin Lu, Co-Chair; Hao Zhang, Co-Chair; Anastasios Tsiatis, Member; Daowen Zhang, Member; David Baumer, Graduate School Representative
- Statistical Methods in Genetic Association Studies and a Genetic Risk Score for Predictive Modeling of Disease Risk: from Gene Discovery to Translation.(2013-04-05) Che, Ronglin; Wenbin Lu, Co-Chair; Alison Motsinger-Reif, Co-Chair; Anastasios Tsiatis, Member; Matthew Breen, Member
- Statistical Modeling with Covariates Subject to Detection Limits.(2013-04-23) Bernhardt, Paul William; Huixia Wang, Co-Chair; Daowen Zhang, Co-Chair; Marie Davidian, Member; Anastasios Tsiatis, Member; Wenye Wang, Graduate School Representative
- Two-step Methods for Differential Equation Models.(2017-09-07) Tan, Qianwen; Subhashis Ghoshal, Chair; Tao Pang, Graduate School Representative; Anastasios Tsiatis, Member; Wenbin Lu, Member; Charles Smith, Member
- Variable Selection and Inference for Covariate-Adjusted Semiparametric Inference in Randomized Clinical Trials.(2012-03-12) Yuan, Shuai; Marie Davidian, Co-Chair; Hao Zhang, Co-Chair; Dennis Boos, Member; Anastasios Tsiatis, Member; Harold Freeman, Graduate School Representative
