For more information, contact the Colloquium/Seminar Coordinator, Dr. Hokwon Cho
(To see Math Dept Colloquia/Seminars, click next: Math Dept Seminar)
· Fri. 1:00 p.m. September 25, SEB-1240: Dr. Peter Müller
Abstract: We consider statistical inference for high
throughput genomic data. Most traditional statistical methods implicitly
assume independent sampling (conditional on some hyperparameters).
Recognizing the limitations of independent modeling we develop a model that
includes a simple dependence structure across genes (or proteins). The
important features of the proposed model are the ease of representing typical
prior information on the nature of dependencies, model-based parsimonious
representation of the signal as a ordinal outcome, and the use of a coherent
probability model over both, structure and strength of the conjectured
· Fri. 12:30 p.m. November 4, SEB-1240: Dr. Ching-Ti Liu
Abstract: Multiple genes, gene-by-gene interactions, and gene-by-environment interactions are believed to underline most complex diseases. However, such interactions are difficult to identify. While there have been recent successes in identifying genetic variants for complex diseases, it still remains difficult to identify gene-gene and gene-environment interactions. To overcome this difficulty, we propose a forest-based approach and a concept of variable importance. The proposed approach is demonstrated by simulation study for its validity and illustrated by a real data analysis for its use. Analyses of both real data and simulated data based on published genetic models show the effectiveness of our approach.
· Fri. 12:30 p.m. November 20, SEB-1240: Dr. Donatello Telesca
Abstract: Functional data often
exhibit a common shape but also variations in amplitude and phase across
curves. The analysis often proceeds by synchronization of the data through
curve registration. We propose a Bayesian hierarchical model for curve
registration. Our methodology is extended to define a class of probability
models, which combine curve registration with functional mixed effects
modeling, discriminating phase and amplitude variability in a joint fashion.
We discuss this class of models with a focus on penalized smoothing splines
and propose Bayesian inferential procedures based on Markov Chain Monte Carlo
samples from the posterior distribution of the functions of interest. We
illustrate the application of our model using simulated data as well as to
two datasets, namely, the
· Fri. 1:30 p.m. February 19, SEB-1245: Dr. Jeffrey Rosenthal
Abstract: The Metropolis algorithm is a very popular method of approximately sampling from complicated probability distributions, such as those arising in Bayesian inference. A wide variety of proposal distributions and tunings are available, and it can be difficult to choose among them. One possibility is to have the computer automatically "adapt" the algorithm while it runs, to improve and tune on the fly. However, natural-seeming adaptive schemes can destroy the ergodicity properties which are essential for the algorithm to be valid. In this talk, we first discuss general principles about optimizing Metropolis algorithms. We then consider adapting the algorithm, and explain using a very simple graphical example (probability.ca/jeff/java/adapt.html) how ergodicity can fail. We present a theorem which gives simple conditions that ensure ergodicity, and consider several high-dimensional adaptive Metropolis and Metropolis-within-Gibbs examples. Finally, we briefly discuss a preliminary general-purpose adaptive MCMC software package (probability.ca/amcmc). Much of this is joint work with G.O. Roberts.
· Fri. 1:30 p.m. February 26, SEB-1245: Dr. Andrew Martin
Title: Untangling the Causal Effects of Sex on Judging
Abstract: We explore the role of sex in judging by addressing two questions of long-standing interest to political scientists: whether and in what ways male and female judges decide cases distinctly---``individual effects"---and whether and in what ways serving with a female judge causes males to behave differently---``panel effects." While we attend to the dominant theoretical accounts of why we might expect to observe either or both effects, we do not use the predominant statistical tools to assess them. Instead, we deploy a more appropriate methodology: semi-parametric matching, which follows from a formal framework for causal inference. Applying matching methods to thirteen areas of law, we observe consistent gender effects in only one---sex discrimination. For these disputes, the probability of a judge deciding in favor of the party alleging discrimination decreases by about 10 percentage points when the judge is a male. Likewise, when a woman serves on a panel with men, the men are significantly more likely to rule in favor of the rights litigant. These results are consistent with an informational account of gendered judging and are inconsistent with several others. Time permitting, I will discuss the Supreme Court Database websites.
· Fri. 1:30 p.m. April 16, SEB-1245: Dr. Ian McKeague
Department of Biostatistics,
Title: Fractals and finding the locations of differentially expressed genes
Abstract: The statistical literature on gene expression data has mostly been concerned with multiple testing procedures for selecting sets of candidate genes that are differentially expressed between cases and controls. This talk discusses the complementary problem of finding confidence regions for the locations (along a chromosome) of such genes. Bootstrap methods for addressing this problem are introduced. The asymptotic performance of the proposed approach is studied in a functional data analysis framework in which the gene expression profiles are treated as stochastic processes having certain fractal properties.
· Fri. 12:00 p.m. April 30, SEB-1245: Dr. Adrian Dobra
Abstract: We present a computational approach for generating Markov bases for multi-way contingency tables whose cells counts might be constrained by lower and upper bounds. Instead of computing the entire Markov basis in an initial step, this framework finds sets of local moves that connect each table in the reference set with a set of neighbor tables. We construct a Markov chain on the reference set of tables that requires only a set of local moves at each iteration. The union of these sets of local moves forms a dynamic Markov basis. We illustrate the practicality of these algorithms in two numerical examples.
· Thu. 2:00 p.m. May 13, CBC C-122: Dr. Sam Weerahandi
Abstract: In estimating response by a large number of Segments or Subjects, simple regressions yield highly unreliable estimates. The problem can be alleviated by using mixed models. Then BLUP of segment estimates become a function of variance components, which are traditionally estimated by MLE. It is well known that MLE could yield negative and/or unreliable estimates for variance components. We proposed a generalized inference based estimation method which is substantially superior to MLE in this class of applications. The utility of the method will be demonstrated involving a pharmaceutical marketing application where one needs to estimate hundreds of thousands of parameters. A demo of a tool that utilizes estimated responses in Profit Maximization will be given with some hypothetical and yet representative data.