Brown University Center for Statistical Sciences Seminar
Abstract: Increasingly in biomedical studies, health status is inferred through a series of measurements or indicators. For example, disability in older persons is often quantified as a series of categorical responses to questions about ability to perform routine tasks of living. Effectively analyzing such data for associations with risk factors remains a challenge, particularly when it is necessary to track the responses over time. In this talk, a latent variable regression methodology is developed for analyzing multiply-measured discrete outcomes. Cross-sectional as well as "marginal" and "transitional" longitudinal models are proposed. Parameter identification and estimation, inference, and treatment of response measurement error are studied. Techniques are developed to diagnose model fit and assess appropriateness of statistical assumptions. The proposed methods are illustrated using visual functioning data from an ongoing gerontological study, including comparison to two competing analytic strategies: empirical summarization of outcomes into a few variables, followed by joint modeling of the summaries as functions of predictors; and, joint modeling of individual outcomes as functions of predictors, accounting for within-person associations. The proposed methodology parsimoniously describes multiply-measured response data, incorporates response measurement error explicitly in modeling, is diagnosable for failure to adequately describe the data, and identifies breakdowns in intended outcome measurement.
LEMS and Electrical Science Seminar
Abstract: Alpha microprocessors have maintained leadership performance since their introduction in 1992. Three generations of microprocessors have been designed by an experienced, highly skilled design team using a proven design methodology. These microprocessors achieve performance by focusing on high frequency design. To facilitate this type of design, the Alpha instruction set architecture (ISA) uses simple fixed length instructions. In addition, Digital's CMOS technologies include specific features to enable high frequency, low-skew clock distribution. Complex circuit styles are used throughout these designs to meet aggressive cycle time goals. Close interaction between all of these disciplines was essential to the success of these microprocessors. The talk will discuss some of the key techniques and their evolution, which enabled Alpha microprocessors to deliver leadership performance.
Department of Mathematics Colloquium
Brown Analysis Seminar
Applied Mathematics Colloquium
Abstract:
The talk will start with a brief introduction to the Black and Scholes
formula, addressed with either a PDE or a probabilistic approach, keeping
in mind in both cases the central economic argument. It will then focus on
so-called path-dependent options, in particular Asian and double-barrier
options, which are very popular in the equity and FX markets and which
raise interesting valuation problems.
The introduction of stochastic time changes and Laplace transforms leads in
both situations to quasi-explicit solutions. For pricing and especially for
hedging, the results are superior to those obtained with Monte-Carlo
simulations.
Biography: Helyette Geman is Professor of Finance at the University Paris IX Dauphine and at ESSEC Graduate Business School. She is a graduate from Ecole Normale Superieure, holds a master's degree in theoretical physics and a Ph.D. in Mathematics from the University Paris VI Pierre et Marie Curie and a Ph.D. in Finance from the University Paris I Pantheon Sorbonne. Dr. Geman is also a member of honor of the French Society of Actuaries. Previously a Director at Caisse des Depots in charge of Research and Development, she is currently a scientific adviser for major financial institutions and insurance companies. Dr. Geman has extensively published in international journals and received in 1993 the first prize of the Merrill Lynch awards for her work on exotic options and in 1995 the first AFIR (Actuarial Approach for Financial Risk) International prize for her pioneering research on catastrophe and extreme events derivatives. She is the co-founder and editor of European Finance Review, associate editor of the journals Mathematical Finance, Geneva Papers on Insurance, Applied Stochastic Models and Data Analysis, Net Exposure, and co-Chair of the French branch of the International Association of Financial Engineers.
PDE Seminar
<--- 1997 Index