Statistics Seminar, 2008-2009

FALL 2008 SEMINAR TALKS:

(Fall 2008, Seminar No. 1)

SPEAKER: Prof. Hosam M. Mahmoud
The George Washington University,
Washington, D.C. 20052, U.S.A.

TITLE: The Polya Process and Applications

TIME AND PLACE:  Thursday, September 18, 2008, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: We investigate the Polya process, which underlies an urn of white and blue balls growing in real time. A partial differential equation governs the evolution of the process. Some special cases are amenable to exact and asymptotic solution: they include the (forward or backward) diagonal processes, and the Ehrenfest process.

Applications of standard (discrete) urns and their analogue when embedded in real time include several classes of random trees that have applications in computer science, epidemiology and philology. We shall present some of these applications.

NO Talk: AMSC celebration.

SPEAKER: Anastasia Voulgaraki, M.Sc.
University of Maryland
College Park, MD 20742, U.S.A.

TITLE: Estimation of Death Rates in US States With Small Subpopulations

TIME AND PLACE:  Thursday, October 2, 2008, 3:30pm
            Room 1313, Math Bldg

ABSTRACT: The National Center for Health Statistics (NCHS) uses observed mortality data to publish race-gender specific life tables for individual states decennially. At ages over 85 years, the reliability of death rates based on these data is compromised to some extent by age misreporting. The eight-parameter Heligman-Pollard parametric model is then used to smooth the data and obtain estimates/extrapolation of mortality rates for advanced ages. In States with small sub-populations the observed mortality rates are often zero, particularly among young ages. The presence of zero death rates makes the fitting of the Heligman-Pollard model dificult and at times outright impossible. In addition, since death rates are reported on a log scale, zero mortality rates are problematic. To overcome observed zero death rates, appropriate probability models are used. Using these models, observed zero mortality rates are replaced by the corresponding expected values. This enables using logarithmic transformations, and the fitting of the Heligman-Pollard model to produce mortality estimates for ages 0-130 years.

SPEAKER: Prof. Ali Arab
Georgetown University
Washington, D.C. 20057, U.S.A.

TITLE: Efficient Parameterization of PDE-Based Dynamics for Spatio-Temporal Processes

TIME AND PLACE:  Thursday, October 16, 2008, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: Spatio-temporal dynamical processes in the physical and environmental sciences are often described by partial differential equations (PDEs). The inherent complexity of such processes due to high- dimensionality and multiple scales of spatial and temporal variability is often intensified by characteristics such as sparsity of data, complicated boundaries and irregular geometrical spatial domains, among others. In addition, uncertainties in the appropriateness of any given PDE for a real-world process, as well as uncertainties in the parameters associated with the PDEs are typically present. These issues necessitate the incorporation of efficient parameterizations of spatio-temporal models that are capable of addressing such characteristics. A hierarchical Bayesian model characterized by the PDE-based dynamics for spatio-temporal processes based on their Galerkin finite element method (FEM) representations is developed and discussed. As an example, spatio-temporal models based on advection-diffusion processes are considered. Finally, an application of the hierarchical Bayesian modeling approach is presented which considers the analysis of tracking data obtained from DST (data storage devices) sensors to mimic the pre-spawning upstream migration process of the declining shovelnose sturgeon.

SPEAKER: Prof. Sandra Cerrai
University of Maryland
College Park, MD 20742, U.S.A.

TITLE: A central limit theorem for some reaction-diffusion equations with fast oscillating perturbation

TIME AND PLACE:  Thursday, October 23, 2008, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: We study the normalized difference between the solution $u_\e$ of a reaction-diffusion equation in a bounded interval $[0,L]$ perturbed by a fast oscillating term, arising as the solution of a stochastic reaction-diffusion equation with a strong mixing behavior, and the solution $\bar{u}$ of the corresponding averaged equation. We assume the smoothness of the reaction coefficient and we prove that a central limit type theorem holds. Namely, we show that the normalized difference $(u_\e-\bar{u})/\sqrt{\e}$ converges weakly in $C([0,T];L^2(0,L))$ to the solution of the linearized equation where an extra Gaussian term appears.

SPEAKER: Prof. Edward J. Wegman
George Mason University
Fairfax, VA 22030, U.S.A.

TITLE: Mixture Models for Document Clustering

TIME AND PLACE:  Thursday, October 30, 2008, 3:30pm
            Colloquium Room 3206, Math Build (not the usual room.)
Talk sponsored by Math Stat and the Stat Consortium. There will be a eception following the talk in the Math Lounge 3201.

ABSTRACT: Automatic clustering and classification of documents within corpora is a challenging task. Often, comparing word usage within the corpus, the so-called bag-of-words methodology, does this. The lexicon for a corpus can indeed be very large. For the example of 503 documents that we consider, there are more than 7000 distinct terms and more than 91,000 bigrams. This means that a term vector characterizing a document will be approximately 7000 dimensional. In this talk, we use an adaptation of normal mixture models with 7000 dimensional data to locate centroids of clusters. The algorithm works surprisingly well and is linear in all the size metrics.

SPEAKER: Dr. Michail Sverchkov
BAE Systems IT and Bureau of Labor Statistics
Washington, DC 20212-0001, U.S.A.

TITLE: On Estimation of Response Probabilities when Missing Data are Not Missing at Random

TIME AND PLACE:  Thursday, November 6, 2008, 3:30pm
            Room 1313, Math Bldg

ABSTRACT: Most methods that deal with the estimation of response probabilities assume either explicitly or implicitly that the missing data are 'missing at random' (MAR). However, in many practical situations this assumption is not valid, since the probability to respond often depends directly on the outcome value. The case where the missing data are not MAR (NMAR) can be treated by postulating a parametric model for the distribution of the outcomes before non-response and a model for the response mechanism. The two models define a parametric model for the joint distribution of the outcomes and response indicators, and therefore the parameters of these models can be estimated by maximization of the likelihood corresponding to this distribution. Modeling the distribution of the outcomes before non-response, however, can be problematic since no data are available from this distribution.

In this talk we propose an alternative approach that allows to estimate the parameters of the response model without modelling the distribution of the outcomes before non-response. The approach utilizes relationships between the population, the sample and the sample complement distributions derived in Pfeffermann and Sverchkov (1999, 2003) and Sverchkov and Pfeffermann (2004).

Key words: sample distribution, complement-sample distribution, prediction under informative sampling or non-response, estimating equations, missing information principle, non-parametric estimation

SPEAKER: Prof. Malay Ghosh
University of Florida
Gainesville, FL 32611-8545 , U.S.A.

TITLE: Bayesian Benchmarking in Small Area Estimation

TIME AND PLACE:  Thursday, November 13, 2008, 3:30pm
            Room 1313, Math Bldg

ABSTRACT: Abstract

SPEAKER: Prof. Gauri S. Datta
University of Georgia
Athens, GA 30602, U.S.A.

TITLE: Estimation of Small Area Means under Measurement Error Models

TIME AND PLACE:  Tuesday, November 18, 2008, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: In recent years demand for reliable estimates for characteristics of small domains (small areas) has greatly increased worldwide due to growing use of such estimates in formulating policies and programs, allocating government funds, planning regional development, and marketing decisions at local level. However, due to cost and operational considerations, it is seldom possible to procure a large enough overall sample size to support direct estimates of adequate precision for all domains of interest. It is often necessary to employ indirect estimates for small areas that can increase the effective domain sample size by borrowing strength from related areas through linking models, using census and administrative data and other auxiliary data associated with the small areas. To this end, the nested error regression model for unit-level data and the Fay-Herriot model for the area-level data have been widely used in small area estimation. These models usually treat that the explanatory variables are measured without error. However, explanatory variables are often subject to measurement error. Both functional and structural measurement error models have been recently proposed by researchers in small area estimation to deal with this issue. In this talk, we consider both functional and structural measurement error models in discussing empirical Bayes (equivalently, empirical BLUP) estimation of small area means.

SPEAKER: Dr. Gang Zheng
Office of Biostatistics Research, National Heart, Lung and Blood Institute
6701 Rockledge Drive, Bethesda, MD 20892-7913, U.S.A.

TITLE: On Robust Tests for Case-Control Genetic Association Studies

TIME AND PLACE:  Thursday, November 20, 2008, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: When testing association between a single marker and the disease using case-control samples, the data are presented in a 2x3 table. Pearson's Chi-square test (2 df) and the trend test (1 df) are commonly used. Usually one does not know which of them to choose. It depends on the unknown genetic model underlying the data. So one could either choose the maximum (MAX) of a family of trend tests over all possible genetic models (Davies, 1977, 1987) or take the smaller p-values (MIN2) of Pearson's test and the trend test (Wellcome Trust Case-Control Consortium, 2007).

We show that Pearson's test, the trend test and MAX are all trend tests with different types of scores: data-driven or prespecified and restricted or not restricted. The results provide insight into the properties that MAX is always more powerful than Pearson's test when the genetic model is restricted and that Pearson's test is more robust when the model is not restricted. For the MIN2 of WTCCC (2007), we show that its null distribution can be derived, so the p-value of MIN2 can be obtained. Simulation is used to compare the above four tests. We apply MIN2 to the result obtained by The SEARCH Collaborative Group (NEJM, August 21, 2008) who used MIN2 to detect a SNP in a genome-wide association study, but could not report the p-value for that SNP when MIN2 was used.

References:

1. Joo J, Kwak M, Ahn K and Zheng G. A robust genome-wide scan statistic of the Wellcome Trust Case-Control Consortium. Biometrics (to appear).
2. Zheng G, Joo J and Yang Y. Pearson's test, trend test, and MAX are all trend tests with different type of scores. Unpublished manuscript. See Slides.

SPEAKER: Dr. Yair Goldberg
Hebrew University of Jerusalem,
Mt. Scopus, Jerusalem, Israel

TITLE: Manifold learning: The price of normalization

TIME AND PLACE:  Tuesday, November 25, 2008, 3:30pm
             Room 1313, Math Bldg (room number may change)

ABSTRACT: The problem of finding a compact representation for high-dimensional data is encountered in many areas of science and has motivated the development of various dimension-reducing algorithms. The Laplacian EigenMap dimension-reducing algorithm (Belkin & Niyogi, 2003) is widely used for its intuitive approach and computational simplicity, claims to reveal the underlying non-linear structure of high-dimensional data.

We present a general class of examples in which the Laplacian EigenMap fails to generate a reasonable reconstruction of the data given to it. We both prove our results analytically and show them empirically. This phenomenon is then explained with an analysis of the limit-case behavior of the Laplacian EigenMap algorithm both using asymptotics and the continuous Laplacian operator. We also discuss the relevance of these findings to the algorithms Locally Linear Embedding (Roweis and Saul, 2000), Local Tangent Space Alignment (Zhang and Zha, 2004), Hessian Eigenmap (Donoho and Grimes, 2004), and Diffusion Maps (Coifman and Lafon, 2006).

SPEAKER: Mitchell H. Gail, M.D., Ph.D.
Senior Investigator Biostatistics Branch, Div. Cancer Epidemiology & Genetics, National Cancer Institute,
Rockville, MD, 20852, U.S.A.

TITLE: Absolute Risk: Clinical Applications and Controversies

DATE/TIME:  Friday, December 5, 2008, 3:15--5:00pm

PLACE: Engineering Building Lecture Hall EGR 1202             

Immediately following the talk there will be a formal 25-minute Discussion, with a Reception to follow that.

ABSTRACT: Absolute risk is the probability that a disease will develop in a defined age interval in a person with specific risk factors. Sometimes absolute risk is called "crude" risk to distinguish it from the cumulative "pure" risk that might arise in the absence of competing causes of mortality. After defining absolute risk, I shall present a model for absolute breast cancer risk and illustrate its clinical applications. I will also describe the kinds of data and approaches that are used to estimate models of absolute risk and two criteria, calibration and discriminatory accuracy, that are used to evaluate absolute risk models. In particular, I will address whether well calibrated models with limited discriminatory accuracy can be useful.

Dr. Mitchell Gail received an M.D. from Harvard Medical School in 1968 and a Ph.D. in statistics from George Washington University in 1977. He joined NCI in 1969, and served as chief of the Biostatistics Branch from 1994 to 2008. Dr. Gail is a Fellow and former President of the American Statistical Association, a Fellow of the American Association for the Advancement of Science, an elected member of the American Society for Clinical Investigation, and an elected member of the Institute of Medicine of the National Academy of Sciences. He has received the Spiegelman Gold Medal for Health Statistics, the Snedecor Award for applied statistical research, the Howard Temin Award for AIDS Research, the NIH Director's Award, and the PHS Distinguished Service Medal.

Discussant: Professor Bilal Ayyub
Department of Civil & Environmental Engineering, UMCP
College Park, MD, 20742, U.S.A.


Discussion, 4:15pm: Engineering perspectives on Risk

Professor Ayyub is a Professor of Civil and Environmental Engineering at the University of Maryland College Park and Director of the Center for Technology and Systems Management. He is a Fellow of the ASCE, ASME, and SNAME.

SPEAKER: Dr. Janice Lent
Energy Information Administration
Washington, DC 20585, U.S.A.

TITLE: Some Properties of Price Index Formulas

TIME AND PLACE:  Thursday, December 11, 2008, 3:30pm
            Room 1313, Math Bldg

ABSTRACT: Price indexes are important statistics that move large amounts of money in the U.S. economy. In order to adjust monetary figures for inflation/deflation, we must develop methods of using sample data to estimate changes in the value of a currency. A vast array of target price index formulas are discussed in the economics literature. In this seminar, we will present some of the formulas that are widely used by government statistical agencies as targets for price index estimation. We will examine and compare some of the properties of these formulas, including underlying economic assumptions, ease of estimation, and sensitivity to extreme values.

SPEAKER: Dr. Zhe Lin
Institute for Advanced Computer Studies, University of Maryland
College Park, MD 20742, U.S.A.

TITLE: Recognizing Actions by Shape-Motion Prototypes

TIME AND PLACE:  Thursday, February 12, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: In this talk, I will introduce our recent work on gesture or action recognition based on shape-motion prototypes. During training, a set of action prototypes are learned in a joint shape and motion space via k-means clustering; During testing, humans are tracked while a frame-to-prototype correspondence is established by nearest neighbor search, and then actions are recognized using dynamic prototype sequence matching. Similarity matrices used for sequence matching are efficiently obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distance. Our approach enables robust action matching in very challenging situations (such as moving cameras, dynamic backgrounds) and allows automatic alignment of action sequences by dynamic time warping. Experimental results demonstrate that our approach achieves over 91% recognition rate on a large gesture dataset containing 294 video clips of 14 different gestures, and 100% on the Weizmann action dataset.

SPEAKER: Prof. Refik Soyer
George Washington University
Washington, DC 20052, U.S.A.

TITLE: Information Importance of Predictors

TIME AND PLACE:  Thursday, February 19, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: The importance of predictors is characterized by the extent to which their use reduces uncertainty about predicting the response variable, namely their information importance. Shannon entropy is used to operationalize the concept. For nonstochastic predictors, maximum entropy characterization of probability distributions provides measures of information importance. For stochastic predictors, the expected entropy difference gives measures of information importance, which are invariant under one-to-one transformations of the variables. Applications to various data types lead to familiar statistical quantities for various models, yet with the unified interpretation of uncertainty reduction. Bayesian inference procedures for the importance and relative importance of predictors are developed. Three examples show applications to normal regression, contingency table, and logit analyses.

SPEAKER: Lior Noy
Harvard Medical School
Boston, MA 02115, U.S.A.

TITLE: Studying Eye Movements in Movement Imitation

TIME AND PLACE:  Thursday, February 26, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: People, animals and robots can learn new actions from observation. In order to do so, they need to transform the visual input to motor output. What is the nature of this transformation? What are the visual features that are extracted and used by the imitator? A possible route for answering these questions is to analyze imitatorsN!NG eye movements during imitation. We monitored eye movements of human subjects while they were watching simple, one-arm movements in two conditions. In the watch-only condition the observers were instructed only to watch the movements. In the imitate condition the observers were instructed to watch and then to imitate each movement. Gaze trajectories were compared between the two conditions. In addition, we compared the human behavior to the predications of the Itti-Koch saliency-map model [1]. To determine the similarity among gaze trajectories of different observers we developed a novel comparison method, based on semi-parametric statistics. We compared this method to the more standard usage of cross-correlation scores and show the advantages of this method, in particular its ability to state that two gaze trajectories are either different or similar in a statistically significant way. Our results indicate that: (1)Subjects fixate at both the joints and the end-effectors of the observed moving arms, in contrast to previous reports [2]. (2)The Itti-Koch saliency-map model does not fully account for the human gaze trajectories. (3)Eye movements in movement imitation are similar to each other in the watch-only versus the imitate conditions.

Joint work with: Benjamin Kedem & Ritaja Sur, University of Maryland, and Tamar Flash, Weizmann Institute of Science.

References

[1] L. Itti and C. Koch. A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research, 40:1489-1506, 2000.
[2] M. J. Mataric and M. Pomplun. Fixation behavior in observation and imitation of human movement. Cognitive Brain Research, 7(2):191-202, 1998.

SPEAKER: Prof. Yasmin H. Said (Bio)
George Mason University
Fairfax, Virginia 22030, U.S.A.

TITLE: Microsimulation of an Alcohol System

TIME AND PLACE:  Thursday, March 5, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: Users of alcohol are incorporated into a societal system, which for many purposes resembles an ecological system. An understanding of how this ecological alcohol system works provides an opportunity to evaluate effectiveness of interventions. I use a hybrid directed graph social network model calibrated with conditional probabilities derived from actual data with the idea of reproducing the experience of acute outcomes reflecting undesirable individual and societal outcomes. In the present model, I also approximate geospatial effects related to transportation as well as temporal effects. Drinking behaviors among underage users can be particularly harmful from both a societal and individual perspective. Using the model based on data from experiences in Fairfax County, Virginia, I am able to reproduce the multinomial probability distribution of acute outcomes with high accuracy using a microsimulation of all residents of Fairfax, approximately 1,000,000 agents simulated. By adjusting conditional probabilities corresponding to interventions, I am able to simulate the effects of those interventions. This methodology provides an effective tool for investigating the impact of interventions and thus provides guidance for public policy related to alcohol use.

SPEAKER: Dr. Philip Rosenberg
Biostatistics Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH
Rockville, MD 20852-4910, U.S.A.

TITLE: Proportional Hazards Models and Age-Period-Cohort Analysis of Cancer Rates

TIME AND PLACE:  Thursday, March 12, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: Age-period-cohort (APC) analysis is widely used in cancer epidemiology to model trends in cancer rates. We develop methods for comparative APC analysis of two independent cause-specific hazard rates assuming that an APC model holds for each one. We construct linear hypothesis tests to determine whether the two hazards are absolutely proportional, or proportional after stratification by cohort, period, or age. When a given proportional hazards model appears adequate, we derive simple expressions for the relative hazards using identifiable APC parameters. We also construct a linear hypothesis test to assess whether the logarithms of the fitted age-at-event curves are parallel after adjusting for possibly heterogeneous period and cohort effects, a relationship that can hold even when the expected hazard rates are not proportional. To assess the utility of these new methods, we surveyed cancer incidence rates in Blacks versus Whites for the leading cancers in the United States, using data from the National Cancer Institute's Surveillance, Epidemiology, and End Results Program. Our comparative survey identified cancers with parallel and crossing age-at-onset curves, cancers with rates that were proportional after stratification by cohort, period, or age, and cancers with rates that were absolutely proportional. Proportional hazards models provide a useful statistical framework for comparative APC analysis.

SPEAKER: Dr. Hormuzd Katki
Biostatistics Branch, Division of Cancer Epidemiology and Genetics, National Cancer Institute, NIH, DHHS
Rockville, MD 20852-4910, U.S.A.

TITLE: Insights into p-values and Bayes Factors from False Positive and False Negative Bayes Factors

TIME AND PLACE:  Thursday, March 26, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: The Bayes Factor has stronger theoretical justification than p-values for quantifying statistical evidence, but when the goal is hypothesis testing, the Bayes Factor yields no insight about false positive vs. false negative results. I introduce the False Positive Bayes Factor (FPBF) and the False Negative Bayes Factor (FNBF) and show that they are approximately the two components of the Bayes Factor. In analogy to diagnostic testing, the FPBF and FNBF provide additional insight not obvious from the Bayes Factor. FPBF & FNBF require only the p-value and the power under an alternative hypothesis, forging a new link of p-values to Bayes Factors. This link can be exploited to understand differences in inferences drawn by Bayes Factors versus p-values. In a genome-wide association study of prostate cancer, FPBF & FNBF help reveal the two SNP mutations declared positive by p-values and Bayes Factors that with future data turned out to be false positives.

SPEAKER: Dr. Hiro Hikawa
Department of Statistics, George Washington University
Washington, DC 20052, U.S.A.

TITLE: Robust Peters-Belson Type Estimators of Measures of Disparity and their Applications in Employment Discrimination Cases

TIME AND PLACE:  Thursday, April 16, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: In discrimination cases concerning equal pay, the Peters-Belson (PB) regression method is used to estimate the pay disparities between minority and majority employees after accounting for major covariates (e.g., seniority, education). Unlike the standard approach, which uses a dummy variable to indicate protected group status, the PB method first fits a linear regression model for the majority group. The resulting regression equation is then used to predict the salary of each minority employee by using their individual covariates in the equation. The difference between the actual and the predicted salaries of each minority employee estimates the pay differential for that minority employee, which takes into account legitimate job-related factors. The average difference estimates a measure of pay disparity. In practice, however, a linear regression model may not be sufficient to capture the actual pay-setting practices of the employer. Therefore, we use a locally weighted regression model in the PB approach as a specific functional form of the relationship between pay and relevant covariates is no longer needed. The statistical properties of the new procedure are developed and compared to those of the standard methods. The method also extends to the case with a binary (1-0) response, e.g., hiring or promotion. Both simulation studies and re-analysis of actual data show that, in general, the locally weighted PB regression method reflects the true mean function more accurately than the linear model, especially when the true function is not a linear or logit (for a 1-0 response) model. Moreover, only a small loss of efficiency is incurred when the true relation follows a linear or logit model.

SPEAKER: Dr. Tsong Yi (Bio)
Division of Biometrics VI, OB/OTS/CDER, FDA
Silver Spring, MD 20993, U.S.A.

TITLE: Multiple Testing Issues in Thorough QTc Clinical Trials

TIME AND PLACE:  Thursday, April 23, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: Clinical trial endpoint often measured repeatedly at multiple time points with the objective to show either that the test treatment is more effective than control treatment at at-least one time point or to show that it is more effective than control treatment at all time points. With either objective, it involves with multiple comparisons and the issues of type I error rate control. We illustrate the problem with the example of thorough QT clinical trials. The ICH E14, 2005 defined that drug-induced prolongation of QT interval as evidenced by an upper bound of the 95% confidence interval around the mean effect on QTc of 10 ms. Further more it defined that a negative thorough QT/QTc study is one in which the upper bound of the 95% one-sided confidence interval for the largest time-matched mean effect of the drug on the QTc interval excludes 10 ms. It leads to the requirement of showing non-inferiority of the test treatment to placebo at multiple time points. Conventionally, it is carried out by testing multiple hypotheses at 5% type I error rate each. The multiple comparison concern of this analysis is conservativeness when the number of tests is many. On the other hand, when the study result is negative, ICH E14 recommended to validate the negative result by showing that the study population is sensitive enough to show at least 5 ms prolongation of QTc interval of a carefully selected positive control. The validation test is often carried out by demonstrating that the mean difference between positive control and placebo is greater than 5 ms at at-least one of the selected few time points. The multiple comparison nature of the validation test led to the concerns of type I error rate inflation. Both of the multiple comparison issue can be represented by the biasness of using the maximum of the estimates of treatment difference as the estimate of the maximum of the expected differences. We will discuss a few proposed approaches to address the problem.

SPEAKER: Dr. Alan Dorfman Dr. Alan Dorfman
Bureau of Labor Statistics, U.S. Department of Labor
NE Washington, DC 20212-0001, U.S.A.

TITLE: Nonparametric Regression and the Two Sample Problem

TIME AND PLACE:  Thursday, April 30, 2009, 3:30pm
             Room 1313, Math Bldg

ABSTRACT: The two sample problem: two distinct surveys gather information on a variable y of interest from a single frame, differing perhaps in sample design and sample size, but with common auxiliary information x. How should we combine the data from the surveys to get a single estimate? Nonparametric regression: Models are often used in survey sampling to sharpen inference on y based on more complete knowledge of an auxiliary variable x. Because of the tentativeness of models in most circumstances, samplers typically buttress their model-based inference by embedding it in a design-based framework ("model assisted" estimation). An alternate approach is to use very weak models and nonparametric regression. A simple two sample problem is described and several approaches to handling it described. A simple, somewhat disguised version of nonparametric regression provides a nice solution. Some problematic and controversial aspects of nonparametric regression in survey sampling are discussed.