Statistics Seminar at Georgia State University

Fall 2021-Spring 2022, Fridays 3:00-4:00pm, Virtual Seminar

Organizer: Yichuan Zhao

If you would like to give a talk in Statistics Seminar, please send an email to Yichuan Zhao at yichuan@gsu.edu



2:00-3:00pm, April 15, 2022, Virtual Colloquium, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=m82744e7a21ff67db19746086edb89553 , Dr. Lily Wang, Professor, Department of Statistics, George Mason University,
Big spatial data learning: a parallel solution

Abstract: Nowadays, we are living in the era of “Big Data.” A significant portion of big data is big spatial data captured through advanced technologies or large-scale simulations. Explosive growth in spatial and spatiotemporal data emphasizes the need for developing new and computationally efficient methods and credible theoretical support tailored for analyzing such large-scale data. Parallel statistical computing has proved to be a handy tool when dealing with big data. In general, it uses multiple processing elements simultaneously to solve a problem. However, it is hard to execute the conventional spatial regressions in parallel. This talk will introduce a novel parallel smoothing technique for generalized partially linear spatially varying coefficient models, which can be used under different hardware parallelism levels. Moreover, conflated with concurrent computing, the proposed method can be easily extended to the distributed system. Regarding the theoretical support of estimators from the proposed parallel algorithm, we first establish the asymptotical normality of linear estimators. Secondly, we show that the spline estimators reach the same convergence rate as the global spline estimators. The proposed method is evaluated through extensive simulation studies and an analysis of the US loan application data.

2:00-3:00pm, March 25, 2022, Virtual Colloquium, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=maae9da0ce06ddc035e87c0b746b524a8 , Dr. Tony Sun, Curators Distinguished Professor, Department of Statistics, University of Missouri,
Distinguished Lecture: Simultaneously Variable Section and Estimation for Interval-Censored Failure Time Data

Abstract: Variable selection is a common task in many fields and also a hot topic for the analysis of high-dimensional data. Correspondingly, many methods have been developed and among them, a general type of procedure is the penalized approach. In this talk, we will discuss variable selection when one faces interval-censored failure time data, a general type of failure time data that can occur in many areas including demographical studies, economic studies, medical studies and social sciences. For the problem, some recently developed penalized procedures will be presented and discussed.

3:00-4:00pm, March 04, 2022, Virtual Statistics Seminar, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=ma826129ec840a83218204e4cf7a983ec , Dr. Xinyi Li, Assistant Professor, School of Mathematical and Statistical Sciences, Clemson University,
Spline Smoothing of 3D Solid Models

Abstract: Over the past two decades, we have seen an exponentially increased amount of point clouds collected in various areas such as geography, environmental sciences, computer graphics, engineering, economics, and medical imaging. These point clouds are usually collections of enormous measurements in space defined by an arbitrary coordinates system, and thus they can also be viewed as a special type of geospatial data. Most existing modeling works focus on reconstructing and modeling the shape based on the point clouds. However, these point clouds usually contain other information besides coordinates, such as the brain activity level in neuroimaging and the grade and type of minerals in the mining industry. Unfortunately, there has been little exploration of the underlying signal and building up a 3D solid model from the point cloud of irregular shapes. To achieve this goal, we propose a class of penalized spline smoothing methods based on the multivariate spline over the tetrahedral partitions in this paper. The proposed method can be used to solve the missing data problem, denoise or deblur the point cloud effectively, and provide a multi-resolution reconstruction of the actual signal. Furthermore, we investigate the theoretical support of the proposed method. Specifically, we establish the convergence rate and asymptotic normality of the proposed estimator and illustrate that the convergence rate achieves the optimal nonparametric convergence rate, and the asymptotic normality holds uniformly. Finally, several simulation examples are conducted to investigate the estimation and prediction performance of the proposed method and compare it with traditional smoothing methods.

3:00-4:00pm, February 18, 2022, Virtual Statistics Seminar, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=m468cb4825270a23007ef366089534d94 , Dr. Ting Zhang, Associate Professor, Department of Statistics, University of Georgia,
High Quantile Regression for Tail Dependent Time Series

Abstract: Quantile regression serves as a popular and powerful approach for studying the effect of regressors on quantiles of a response distribution. However, existing results on quantile regression were mainly developed when the quantile level is fixed, and the data are often assumed to be independent. Motivated by recent applications, we consider the situation where (i) the quantile level is not fixed and can grow with the sample size to capture the tail phenomena; and (ii) the data are no longer independent but collected as a time series that can exhibit serial dependence in both tail and non-tail regions. To study the asymptotic theory for high quantile regression estimators in the time series setting, we introduce a previously undescribed tail adversarial stability condition and show that it leads to an interpretable and convenient framework for obtaining limit theorems for time series that exhibit serial dependence in the tail region but are not necessarily strong mixing. Numerical experiments are provided to illustrate the effect of tail dependence on high quantile regression estimators, where simply ignoring the tail dependence may lead to misleading p-values.

2:00-3:00pm, November 19, 2021, Virtual Colloquium, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=mdcc459e78d6e1b68c54f4c484445b641, Dr. Din Chen, Professor and Executive Director in Biostatistics, College of Health Solutions, Arizona State University,
Distinguished Lecture: Integrative Data Harmonization and Statistical Meta-Analysis

Abstract: Data harmonization and Meta-analysis (MA) is a common statistical approach in evidence-based public health research to combine meta-data from diverse studies to reach a more reliable and efficient conclusion. It can be performed by either synthesizing study-level summary statistics (MA-SS) or modeling individual participant-level data (MA-IPD), if available. However, it remains not fully understood whether the use of MA-IPD indeed gains additional efficiency over MA-SS. In this talk, we review the classical fixed-effects and random-effects meta-analyses, and further discuss the relative efficiency between MA-SS and MA-IPD under a general likelihood inference setting. We show theoretically that there is no gain of efficiency asymptotically by analyzing MA-IPD, provided that the random-effects follow the Gaussian distribution, and maximum likelihood estimation is used to obtain summary statistics. Our findings are further confirmed by extensive Monte-Carlo simulation studies and real data analyses.

3:00-4:00pm, November 05, 2021, Virtual Statistics Seminar, Webex Meeting Link: https://gsumeetings.webex.com/gsumeetings/j.php?MTID=m4dc1b297c92bfaae1d4ee4d1e53d1574 , Dr. Yongli Sang, Department of Mathematics, University of Louisiana at Lafayette,
Depth-based Weighted Jackknife Empirical Likelihood for Non-smooth U-structure Equations

Abstract: In many applications, parameters of interest are estimated by solving some non-smooth estimating equations with a U-statistic structure. Jackknife's empirical likelihood (JEL) approach can solve this problem efficiently by reducing the computation complexity of the empirical likelihood (EL) method. However, like EL, JEL suffers the sensitivity problem to outliers. In this paper, we propose a weighted jackknife empirical likelihood (WJEL) to tackle the above limitation of JEL. The proposed WJEL tilts the JEL function by assigning smaller weights to outliers. The asymptotic of the WJEL ratio statistic is derived. It converges in distribution to a multiple of a chi-square random variable. The multiplying constant depends on the weighting scheme. The self-normalized version of WJEL ratio does not require knowing the constant and hence yields the standard chi-square distribution in the limit. The robustness of the proposed method is illustrated by simulation studies and one real data application.