主講者:	1.施信宏教授 (國立高雄大學) 2.Dr. Sharad Goel (雅虎公司)
講題:	1.A characterization of Levy white noise measures 2.Respondent-Driven Sampling as Markov Chain Monte Carlo
時間:	2008-11-03 (Mon.)  14:00 - 17:00
地點:
Abstract:	(1) In this talk, we reinterpret the Stein's identities for normal and Poisson distributions by relating to the theory of quantum probability. From this point of view, we will present a characterization theorem of Levy white noise measures associated with a Levy spectrum having finite second moment. As an application, a Stein-type identity for infinitely divisible distributions will be obtained. (2) Respondent-driven sampling (RDS) is a recently introduced, and now widely used, technique for estimating disease prevalence in hidden populations. The sample is collected through a form of snowball sampling where current sample members recruit future sample members. We reinterpret respondent-driven sampling as Markov chain Monte Carlo (MCMC) importance sampling, and examine the effects of community structure and recruitment methodology on the variance of RDS estimates. Past work on RDS has assumed that the variance of RDS estimates is primarily affected by segregation between healthy and infected individuals. We examine an illustrative model to show that this network feature, while important, in isolation tends to significantly underestimate the effects of community structure on RDS estimates. We also show that variance is increased by a sample design feature which allows sample members to recruit multiple future sample members. Our observations are further substantiated by network data collected as part of the National Longitudinal Study of Adolescent Health. This is joint work with Matthew Salganik.
	|| Close window ||