Title: Did the U.S. Supreme Court Interpret a Disparity Measure Based on Two Percentiles Correctly? Statistical Aspects of the Zuni School District 89 v. U.S. Department of Education case.

Speaker: Joseph L. Gastwirth
Professor of Statistics and Economics
Department of Statistics
George Washington University

Abstract: Before describing the history of the case and the final decision, we will go through some questions concerning the interpretation of the statute at issue in the case. The views of the attendees will be compared with statisticians the author surveyed in a previous article about the method of calculation of the disparity measure that was stimulated by the split decision rendered by the 10th Circuit Court of Appeals. Then the majority and dissenting opinions will be discussed. Several of the arguments presented to the Court, e.g.  Calculating a measure of educational funding disparity on aggregate (school district data) yields an approximation to the value the same measure would have if it was calculated on educational expenditures on each pupil will be shown to be statistically unsound. If time permits, other statistical aspects of the decision will be questioned.

Date : Friday, 7th September

Time: 11:00-12:00 noon

Location: DUQUES 255, 2201 G Street, N.W., Washington D.C.

Title: Multi-stage Sampling for Genetic Studies

Speaker: Dr. Gang Zheng
Mathematical Statistician
Office of Biostatistics Research
National Heart, Lung and Blood Institute, NIH

Abstract:
In the first part of the talk, I will review various multi-stage sampling in classical genetic linkage and association studies. This part does not involve much statistics. In the second part, I will focus on a cost-effective two-stage design for genome-wide case-control association studies. Some test statistics for this two-stage design will also be discussed. Most of the talk is based on an article with Robert Elston and Danyu Lin to appear in Annual Review of  Genomics and Human Genetics (Sept 2007).

Date: Friday, Sept 28th, 2007

Time: 11:00-12:00 noon

Location:
DUQUES 255, 2201 G Street, N.W., Washington D.C.

Title: Limitations of the Non-homogeneous Poisson Process (NHPP) Model for Analyzing Software Reliability Data

Speaker: Dr. Sudip Bose
Department of Statistics
The George Washington University

Abstract:
Software failure data can be analyzed to provide statistical estimates of the reliability of software, which are useful for assessing its quality, and for determining the date of release of a software package.  The non-homogeneous Poisson process (NHPP) model is one of the models most widely used for describing and analyzing software failure processes. NHPP models in which the expected number of errors over infinite observation time is finite, are called NHPP-I models.

Our research proves a key statistical limitation of NHPP-I models, namely inconsistency of parameter estimates.  In other words, even if the process is observed for an arbitrarily long time one cannot estimate unknown parameters of the model very accurately. The inconsistency feature is a consequence of a representation of an NHPP-I model as a mixture of General Order Statistics or GOS models (Raftery, 1987) and holds more generally for mixture distributions in broader settings, and not just for the NHPP model for software failures. This result also has implications for a Bayesian analysis of NHPP models.

We show that optimal unbiased estimation of any parametric function in an NHPP-I model essentially reduces to estimating related parametric functions of the underlying GOS model. We discuss other known features of an NHPP model that are not consistent with certain intuitive features of software failure processes and reliability growth.

This talk is based on joint research with my departmental colleagues, Professors Tapan Nayak and Subrata Kundu.

Time: 11:00am-12:00pm, Friday, Oct 19, 2007

Location: DUQUES 255, 2201 G Street, N.W., Washington D.C.

Fourth Symposium : Frontiers of Statistical, Mathematical and Computational Sciences (SMCS)

(26th and 27th October, 2007)

Day I: Friday, 26 October, 2007                 

Location: Room #103, Funger Hall
                   2201 G Street, NW
                   Washington, DC

0915-0930       Opening Remarks
                    
                      Dean Marguerite (Peg) Barratt, Columbian College of Arts and Sciences, and
                      Professor of Psychology, The George Washington University

0930-1030       Session I     Chair: Dr. Chris Arney.  Army Research Office

  Modeling Military Retention Under Alternative Compensation Systems
 James Hosek, RAND Corporation

Break

 1100-1300       Session II    Chair: Professor Tapan Nayak, GWU

Markovian Models in Cost-Effectiveness Analysis,
Joseph Gardiner, Michigan State University

Statistical Methods for Health Related QOL,
 Mounir Mesbah, Paris VI, Paris, France

 Lunch Break

1520-1620       Session III   Chair: Professor Refik Soyer, GWU

Estimating Health –Related Quality of Life,
Anthony O’Hagan, University of Sheffield, Sheffield, UK

 Day 2: Saturday, 27 October, 2007                

 Location: Room #108, Funger Hall
                   2201 G Street, NW
                   Washington, DC

0930-1145     Session IV   Chair: Professor Qing Pan, GWU

Quality of Life Technology-The Confluence of Engineering, Clinical, and Social Science,
Rory Cooper, University of Pittsburgh (Introduced by Professor Reza Modarres, GWU) 

Challenges in Evidence Synthesis: An End-of-Life Care Systematic Review,
Sally Morton, RTI International (Introduced by Professor Nozer Singpurwalla, GWU)

1145- 1330   Reception/Mixer

1330-1430     Session V   Chair: Professor Hosam Mahmoud, GWU

Characterizing and Mechanically Replicating Human Movement,
 Roger Brockett, Harvard University

1445              Adjourn

Contact Details: Dr. Jagdish Chandra, Research Professor, Department of Statistics, The George Washington University, Washington, DC. Tel: (202) 994-0179; E-mail: jchandra@gwu.edu

Title: Multiphase Regression Models for Assessing Highly Multivariate Measurement Systems

Speaker: Dr. Z.Q. John Lu
National Institute of Standards and Technology
Gaithersburg, MD

Abstract:
While there exist some nice models for the measurement process of scalar and small-scale analytical chemistry experiments, there is lack of understanding and tools for establishing the standards and performance of high throughput measurement systems, such as mRNA microarray measurements. An ongoing program at NIST on gene expression microarray experiments has demonstrated some potential approaches, including some performance metrics for scanner microarray measurement, and use of spike-in experiments in calibration and validation. I will describe a class of multiphase and nonlinear regression models used in these studies, and show how these general measurement models can accommodate for the wide exponential range of signal variation while accounting for the background error, multiplicative signal error, instrument saturation at high intensity, and how they can be adapted to model the highly parallel and multivariate nature of modern biochemical experiments.

Time: Friday,11:00am-12:00noon, Nov 2, 2007.

Location: DUQUES 255, 2201 G Street, N.W., Washington D.C.