Coming Soon…
THIS JUST IN: There has never been a better time to be a statistician.
Texas A&M Statistics is hoping to capitalize on this current trend and our decades of success as a department by embarking on a unique effort to benefit our former, current, and future students. But to do so, we’ll need your help.
We’re exploring the possibility of starting a Statistics Former Student Network to leverage the rich and varied experiences, expertise, and skill sets of our former students to help enrich and extend the educational experiences for our present and prospective graduate and undergraduate students.
Because we believe the short- and long-term success of such a powerful group begins and ends with its potential members, we value your input, ideas, and advice. Please take a moment to complete the following brief survey designed to gauge interest and determine critical next steps.
One of Texas A&M University’s best assets is its people — successful former students, colleagues, and friends with a wealth of institutional, industry, and inspirational knowledge to offer. We encourage you to consider giving back by paying it forward. Advantage, Aggies!
CLICK HERE TO GET STARTED
A network of possibility, created by Texas A&M statisticians for Texas A&M statisticians!
StatLinks
Calendar
September 2017
Departmental Colloquia: Daniel Kowal
September 22, 201711:30 AM / 12:30 PM Blocker Building (BLOC), Room 113 979-845-3141
DANIEL KOWAL 
Department of Statistics
Rice University
"Dynamic Shrinkage Processes"
ABSTRACT
We propose a novel class of dynamic shrinkage processes for Bayesian time series and regression analysis. Building upon the global-local framework of prior construction, in which continuous scale mixtures of Gaussian distributions are employed for both desirable shrinkage properties and computational tractability, we allow the local scale parameters to depend on the history of the shrinkage process. The resulting processes inherit the desirable shrinkage behavior of popular global-local priors, such as the horseshoe prior, but provide additional localized adaptivity, which is important for modeling time series data or regression functions with local features. We construct a highly efficient Gibbs sampling algorithm by adapting successful techniques from stochastic volatility modeling and deriving a Polya-Gamma scale mixture representation of the proposed process. We use dynamic shrinkage processes to produce superior Bayesian trend filtering estimates and posterior credible intervals for irregular curve-fitting of minute-by-minute Twitter CPU usage data, and develop an adaptive time-varying parameter regression model to assess the efficacy of the Fama-French five-factor asset pricing model with momentum added as a sixth factor. Our dynamic analysis of manufacturing and healthcare industry data shows that with the exception of the market risk, no other risk factors are significant except for brief periods.
Friday, 9/22/2017, BLOC 113, 11:30 AM
Departmental Colloquia: Jeffrey D. Hart
September 29, 201711:30 AM / 12:30 PM Blocker Building (BLOC), Room 113 979-845-3141
JEFFREY D. HART 
Department of Statistics
Texas A&M University
"Prior-free Bayes Factors Based on Data Splitting"
ABSTRACT
Bayes factors that do not require prior distributions are proposed for testing one parametric model versus another. These Bayes factors are relatively simple to compute, relying only on maximum likelihood estimates, and are Bayes consistent at an exponential rate for nested models even when the smaller model is true. These desirable properties derive from the use of data splitting and the simplicity of Bayes factors for comparing fully specified models. A simulation study explores practical concerns, and the methodology is illustrated with civil engineering data involving compressive strength of concrete.
Joint work with Matthew Malloure.
Friday, 9/29/2017, BLOC 113, 11:30 AM