(2) Spring '04   RIT on Meta-Analysis. Click here for web-page.
        Briefly, meta-analysis concerns the simultaneous statistical analysis of a number of
        related studies or datasets within a single statistical model. The fact that parameters are
        shared across datasets (e.g. a treatment-effectiveness parameter assumed constant
        across a number of separately conducted clinical studies of  the effectiveness of the same
        treatment regimen for the same disease) allows the possiblity of increasing sensitivity or
        power of statistical tests. However, such an increase in precision comes at the price of
        simultaneous model assumptions whose compatibility with the data must be validated.
        This RIT was an outgrowth of the Fall '03 RIT on Large Cross-Classified Datasets
        (see web-page linked below for details).

            (3)   Spring and Fall '03 RIT on Statistics of Large Cross-Classified Datasets:
        see RITF03 web-page .

            (4)  Intensive Seminar, Fall 2002.  See plan for details.
        In Fall 2002, I ran a `research interaction' seminar including my own graduate advisees
        and others, on the mathematical & statistical topics which more broadly correspond to
        the overlap of my students' thesis projects and most of my own current research interests,
        namely Statistics of Large Cross-Classified Datasets. Roughly speaking, these are
        problems in which there is a large sample-size  n, but where the predictor variables
        and/or cross-classifications of the sample units become more complicated or numerous
        as  n  gets large. Such problems range from Semiparametric Statistical Inference  to
        Order-selection problems in regression and time series, to Classification and Clustering
        as in the Microarray data problems mentioned below. These problems suggest the
        need for a new Asymptotics which explicitly recognizes the growth of the parameter-
        space of a probability model as a function of the size  n  of the dataset.

            (5)  Intensive Seminar, Spring 2002.   See plan for details.
        In Spring 2002, following up on the Fall 2001 seminar described below, I ran an intensive
        seminar on statistical analysis of DNA Microrarrays, for students considering research
        in this area.   Data-analysis figured prominently, performed by me and also by two of the
        several graduate students who participated.
            (6)  Genomics/Microarray Seminar    Fall 2001,    AMSC 699:
        Mathematical Topics in Functional Genomics. Click here for the reading list.

                Other Past Teaching

        (1)   Spring '04, introductory course Stat 470 on Actuarial Mathematics, taught primarily
        from book notes which I wrote. Coverage includes theory of interest, life tables, review of
        probability theory, expectations of time-discounted  insurance costs and premiums
        calculated from life tables, and special models of mortality. See the course web-page
        (from which the main text can be downloaded a chapter at a time) for further details.

        (2)   Spring '04 Stat 798C, Computational Methods in Statistics, a graduate introduction
        to statistical computing with emphasis on the Splus (or R) and SAS computer packages.
        (I also taught this course in Spring '03.)

        (3)   Fall '03, Stat 798S, topics course on Survival Analysis .

        (4)   Spring '03,    Stat 770 , a course on Analysis of Categorical Data, taught out
        of the book, Categorical Data Analysis, by A. Agresti.

                                       Research

(I) Survival data analysis, which includes both semiparametric inference and clinical
           trial design issues. The semiparametric work emphasizes maximization of variants
           of nonparametric likelihoods, especially in Transformation and Frailty models.
           Further work on a general approach to efficient semiparametric estimation described
           in slides from a talk given in the IISA Conference, June 14, 2002. Other current work
           relates to decision-theoretic optimal early-stopping procedures in clinical trials.

For slides of a Stat Seminar I gave in Fall '03 at NIH on asymptotic theory of Semiparametric
statistical procedures in Transformation models, click  here .

(II) Census statistics, specifically demographic modelling of nonresponse to national
            surveys, with particular application to Weighting Adjustment and Small Area
            Estimation (SAE). Much of my small-area estimation work has been directed
            toward the SAIPE (Small Area Income and Poverty Estimation ) program of
            the Census Bureau. See for example the comparative SAE study.
      My methodological research in this area includes small-area and MSE estimation
           from survey data satisfying nonlinearly transformed Fay-Herriot models or
           left-censored Fay-Herriot models.
      Some recent work on internal evaluation of biases due to weighting adjustment for
           nonresponse in a longitudinal survey (SIPP, Survey on Income and Program
           Participation) is described in my Nov. 2007 FCSM talk. A paper describing the
           contents of that talk more fully can be found here.

(III) Large-scale data problems with emphasis on cross-classified data,
           Principal Components (paper on representation of tongue surface during
           speech, recently appeared in the journal Phonetica), and clustering. More recently,
           I have had two students (Yang Cheng and Sophie Tsou) obtain PhD's working
           on Factor Analysis models. Papers extending that work are now in preparation
           and will be posted to this space shortly. A talk I gave on this work in 2005
           [and then again in the Diffusion Wavelet RIT in Fall 2007] can be found here.

(IV) Stochastic processes, currently emphasizing high-dimensional Markov
            processes applied to equilibria in Economics (paper in Journal of Economic
            Theory, for which 2nd pdf file in directory contains Figure); to Protein-folding;
            and to ascertainment of number of distinct DNA `species' from sequencing
            experiments.

           Links

The Campus Statistics Consortium page.

The UMCP Statistics Program home page.

The UMCP Math Department home page.

The University of Maryland home page.

© Eric V Slud, Feb. 13, 2008.