Department of Mathematical Sciences

University of Nevada, Las Vegas


Statistics Colloquium/Seminar Series

2006-2008

 

[2008-2009] [2009-2010] [2010-2011] [Current Year]

 

For more information, contact the Colloquium/Seminar Coordinator, Dr. Hokwon Cho

(To see Math Dept Colloquia/Seminars, click next: Math Dept Seminar)

 

Fall 2006

 

·         Fri. 11:00 a.m. November 3, CBC C-225:  Dr. Nitis Mukhopadhyay

Department of Statistics, University of Connecticut, Storr
Title: A New Two-Stage Sampling Methodology Designed for an Application in Horticulture

Abstract: A horticulturist was considering the number of days each marigold variety took from planting seeds to reach a stage when first bud appeared. The primary interest was to estimate the maximum waiting time between “seeding” and “first budding” among three varieties. It was thought that a 99% confidence interval of width one day would suffice since the data could be recorded with accuracy of one-half day. We assumed a normal distribution for the response variable. The horticulturist provided positive lower bounds for the variances that led to unequal pilot sample sizes.

          Accordingly, a new two-stage sampling design had to be developed and implemented. We will show that the data validated all assumptions made during the course of this investigation.  Some of the important exact as well as large-sample properties of the proposed methodology will also be summarized. Interpretations of the properties would be highlighted with real data.  Finally, we will argue that the new methodology is theoretically superior to an existing methodology in case the pilot sizes could somehow be “chosen” equal. Using the data on hand, the superiority of the new methodology will be indicated.

 

Fall 2007

 

·         Fri. 11:00 a.m. October 12, CBC C-225:  Dr. Junyong Park

Department of Mathematics and Statistics, University of Maryland, Baltimore County
Title: Robust Test for Detecting a Signal in a High Dimensional Sparse Normal Vector

Abstract: We consider the problem of testing whether a high dimensional observation vector has signal, i.e., testing all the mean values are zero versus the alternative that non-zero means exist. The setup is when the dimension of vector is large, and the  mean vector is 'sparse', e.g., the small fraction of mean values is non-zero. We suggest a test which is not sensitive to the exact tail behavior under normality assumption. In particular, if the 'moderate deviation' tail of the distribution is represented as the product of a tail of a standard normal and a `slowly changing' function, our suggested test is robust. In particular, a need for robust test is expected when the observations are of the normalized form where normality assumption is commonly used from C.L.T.

 

·         Fri. 11:30 a.m. November 30, CBC C-225: Dr. Anton Westveld

Department of Mathematical Sciences, University of Nevada, Las Vegas
Title: Modeling Foreign Direct Investment as a Longitudinal Social Network

Abstract: An extensive literature in international and comparative political economy has focused on the how the mobility of capital affects the ability of governments to tax and regulate firms.  The conventional wisdom holds that governments are in competition with each other to attract foreign direct investment (FDI).  Nation-states observe the fiscal and regulatory decisions of competitor governments, and are forced to either respond with policy changes or risk losing foreign direct investment, along with the politically salient jobs that come with these investments.  The political economy of FDI suggests a network of investments with complicated dependencies.

          We propose an empirical strategy for modeling investment patterns in 24 advanced industrialized countries from 1985-2000.  Using bilateral FDI data we estimate how increases in flows of FDI affect the flows of FDI in other countries.  Our statistical model is based on the methodology developed by Westveld & Hoff (2007).  The model allows the temporal examination of each notion's activity level in investing, attractiveness to investors, and reciprocity between pairs of nations.  We extend the model by treating the reported inflow and outflow data as independent replicates of the true value and allowing for a mixture model for the fixed effects portion of the network model.  Using a fully Bayesian approach, we also impute missing data within the MCMC algorithm used to fit the model.  A working paper can be found at: http://faculty.unlv.edu/westveld/Papers/FDI.pdf.

 

Spring 2008

 

·         Friday 2:00 p.m. February 1, CBC C-224: Toby White, Ph.D candidate

Department of Statistics, University of Washington, Seattle
Title: Extensions of Latent Class Transition Models with  Application to Disability Survey Data

Abstract: Latent class transition models are used to partition a population into a small number of relatively homogeneous subgroups so  that the movement of individuals among these subgroups can be followed  through time.  One context for these models involves the U.S. elderly chronically disabled, who may be grouped into one of 4-5 disability  classes which differ by both type and severity of disability.  Such data appear in longitudinal surveys, which can have large assessment  intervals, considerable right and left censoring, and staggered entry  and exit.  Thus, methodology is needed to account for all the possible  time sequences at which individuals can be observed, since traditional  latent class transition models assume a complete set of observations  for each individual.  I develop a group-based modeling approach that encompasses various time sequences of observation, and use the E-M  algorithm with adjustments to estimate model parameters and parameter  standard errors.  I also extend basic latent class transition models  to incorporate age, period, and cohort effects, while satisfying  identifiability constraints.  I illustrate this methodology using ADL  and IADL data from the National Long-Term Care Survey (1982-2004), and  discuss transition probability estimates among classes of varying  disability level and death.

 

·         Friday 11:30 a.m. March 28, CBC C-224: Dr. Yuedong Wang

Department of Statistics and Applied Probability, University of California, Santa Barbara,
Title: Nonlinear Nonparametric Regression Models

Abstract: Almost all of the current nonparametric regression methods such as smoothing splines, generalized additive models and varying coefficients models assume a linear relationship when nonparametric functions are regarded as parameters. In this talk we present a general class of nonlinear nonparametric models that allow nonparametric functions to act nonlinearly. They  arise in many fields as either theoretical or empirical models. We propose new estimation methods based on an extension of the Gauss-Newton method to infinite dimensional spaces and the backfitting procedure. We extend the generalized cross validation and the generalized maximum likelihood methods to estimate smoothing parameters. Connections between nonlinear nonparametric models and nonlinear mixed effects models are established. Approximate Bayesian confidence intervals are derived for inference. We will also present a user friendly R function for fitting these models. The methods will be illustrated using two real data examples.

 

·         Friday 11:30 a.m. May 2, CBC C-224: Dr. Kaushik Ghosh

Department of Mathematical Sciences, University of Nevada, Las Vegas
Title: Joint Modeling of Longitudinal Data and Informative Dropout in the Presence of Multiple   Change points.

Abstract: In longitudinal studies of patients with the Human Immunodeficiency Virus (HIV), objectives of interest often include modeling of individual-level trajectories of HIV Ribonucleic Acid (RNA) as a function of time. Empirical evidence suggests that individual trajectories often possess multiple points of rapid change, which may vary from subject to subject --- both in number and in location. Presence of such changepoints make the modeling of individual viral RNA levels difficult, since usual methods become unsuitable. 

          In this talk, we present a new robust multiple-change point model for longitudinal trajectories. The proposed method uses a joint model to incorporate information from the longitudinal data as well as from informative dropouts, which are common in such studies. A Dirichlet process prior is used to model the distribution of the changepoints. The Dirichlet process leads to a natural clustering, and thus, sharing of information among subjects with similar trajectories. A fully Bayesian approach for model fitting and prediction is implemented using the Gibbs sampler on the ACTG 398 clinical trial data.

 


 

è Statistics Colloquium/Seminar Series