Xiaoyu Li

Auburn University

Testing of Regression Functions with Data Missing at Random

This talk includes two testing problems of regression functions with responses missing at random. One problem is minimum distance model checking. The proposed lack-of-fit tests are based on a class of minimum integrated square distances between a kernel type estimator of a regression function and the parametric regression function being fitted. These tests are shown to be consistent against a large class of fixed alternatives. The corresponding test statistics are shown to have asymptotic normal distributions under the null hypothesis.

Thursday, August 25, 2016 - 3:30pm
Type: 
Statistics Building Room 306

James Monogan

University of Georgia

Slicing Public Opinion for State and National Research

In this paper, we develop and release measures of public ideology in 2010 for the 50 American states, 435 congressional districts, and state legislative districts. We do this using the geospatial statistical technique of kriging, which uses the locations of survey respondents, as well as population covariate values, to predict ideology for simulated citizens in districts across the country.

Thursday, August 18, 2016 - 3:30pm
Type: 
Room 306, Statistics Building 1130

Fei Zou

The University of Florida

On Surrogate Variable Analysis for High Dimensional Genetics and Genomics Data

Unwanted variation in hidden variables often negatively impacts analysis of high-dimensional data, leading to high false discovery rates, and/or low rates of true discoveries.  A number of procedures have been proposed to detect and estimate the hidden variables, including principal component analysis (PCA).  However, empirical data analysis suggests that PCA is not efficient in identifying the hidden variables that only affect a subset of features but with relatively large effects.

Thursday, September 1, 2016 - 3:30pm
Type: 
Pharmacy South Building, Room 101

Peter Song

UM School of Public Health

Confidence Inference Function in Big Data

Statistical inference along with the strategy of divide-and-combine for Big Data analysis has been little studied.  As an effective inferential tool, confidence distribution (CD) has attracted a surge of renewed attention. The essence in constructing confidence distribution pertains to the availability of suitable pivotal quantities, which are usually obtained from the (asymptotical) distribution of point maximum likelihood estimator. We propose to use inference function, from which the parameter estimate is obtained, as the basis of constructing the pivotal.

Thursday, September 22, 2016 - 3:30pm
Type: 
Cohen Room, Statistics Building

Yanyuan Ma

The Pennsylvania State University

Functional and very high dimension reduction

The talk has two components. In the first component, to study the relation between a univariate response and multiple functional covariates, we propose a functional single index model that is semiparametric. The parametric part of the model integrates the linear regression modeling for functional data and the sucient dimension reduction structure. The nonparametric part of the model further allows the response-index dependence or the link function to be unspecied.

Thursday, December 1, 2016 - 3:30pm
Type: 
Room 306, Statistics Building 1130

Maxine Pfannkuch

The University of Auckland, New Zealand

Visualizing chance in introductory probability

Research in the last thirty years has documented the challenges and difficulties in teaching probability and the many misconceptions prevalent in people’s reasoning. There is now a call to reform the approach to teaching probability from a traditional mathematical base to include more emphasis on modeling andinvestigations. Within this spirit of reform we undertook a two-part exploratory study. In the first part we interviewed seven practitioners in order to understand the probability concepts that need to be promoted and the areas of difficulties for students.

Thursday, September 8, 2016 - 3:30pm
Type: 
Room 306, Statistics Building 1130

John Stufken

Arizona State University

Design of Experiments: From Small Data to Big Data

Experimentation is an integral part of science. Exploring or analyzing data leads to new insights, hypotheses, and questions that fuel further investigation. Before data can be explored or analyzed, it needs to be collected. Where possible, this is ideally done through a designed experiment. In a designed experiment, conditions under which observations are made can be controlled, and causal relationships can be studied. A central question in choosing a design is the information that it provides for pursuing the objectives of the experiment.

Monday, June 27, 2016 - 3:30pm
Type: 
Cohen Room, Statistics Building

Snehanshu Saha

PES Institute of Technology, India

Revenue Forecasting in Technological Services: Evidence from Large Data Centers

Data Center is a facility, which houses computer systems and associated components, such as telecommunications and storage systems. It generally includes power supply equipment, communication connections, and cooling equipment. A large data center can use as much electricity as a small town. The emergence of data-center based computing services necessitates the examination of the costs associated with such data centers and the evolution of such costs over time, apropos of market efficiency issues.

Thursday, June 2, 2016 - 3:30pm
Type: 
Cohen Room, Statistics Building

Dr. Daniel Rowe

Marquette University

Modeling and Analysis of Inherently Complex-Valued FMRI Data

In fMRI and fcMRI, the original data measured by the MRI machine are complex-valued, a complex-valued inverse Fourier transform is applied to reconstruct into a complex-valued image. Almost exclusively, the Cartesian real and imaginary images are converted to magnitude and phase images, then the phase half of the data is discarded before statistical analysis. A description of potential biological information in the phase will be provided along with models to compute brain activation using both magnitude and phase. Results from both simulated and experimental data will be presented.

Thursday, April 14, 2016 - 3:30pm
Type: 

Pages

Subscribe to RSS - Colloquium