|
Department of Biostatistics Colloquium Series 2009 - 2010 |
ABSTRACT: None Given.
ABSTRACT: Derivatives of functions play an important role in assessing dynamics. Estimating derivatives from sparse, irregular and noisy measurements, as typically encountered in longitudinal studies, poses challenges. It is demonstrated how these can be overcome under minimal assumptions if one has a sample of random functions, each of which may be sparsely sampled. An application of derivative estimation is empirical dynamics, represented by an empirical first order ordinary differential equation that is constructed from the data and governs the smooth trajectories that generate the observations. This equation combines time-varying coefficients with a smooth drift process. The interpretation of these components is of interest and is illustrated with longitudinal data. The talk is based on work with Bitao Liu and Fang Yao.
ABSTRACT: Abstract: Issues of multiplicity in testing are increasingly being encountered in a wide range of disciplines, as the growing complexity of data allows for consideration of a multitude of possible hypotheses (e.g., does gene xyz affect condition abc). Failure to properly adjust for multiplicities is being blamed for the apparently increasing lack of reproducibility in science. The main purpose of this presentation is to review the different types of multiplicities that are encountered, and to discuss the general approaches to dealing with them that are being adopted by Bayesians, especially in complex situations such as subgroup analysis. Issues that I found surprising will be highlighted, such as the fact that empirical Bayesian approaches to multiplicity adjustment can be seriously flawed.
ABSTRACT: This talk introduces a class of point impact regression models in which the trajectory of a continuous stochastic process, when evaluated at one or more sensitive time points, is associated with a scalar response. A motivation for developing this type of model arises from genome-wide expression studies in which it is of interest to locate genes associated with clinical outcomes. The observed trajectories are assumed to have fractal properties (fractional Brownian motion) in the neighborhood of any sensitive time point. Bootstrap confidence intervals for the sensitive time points are developed. Non-Gaussian limit distributions and faster-than-root-n rates of convergence that depend on the Hurst exponent of the fractional Brownian motion play a central role.
ABSTRACT: This talk surveys confidence intervals that result from inverting score or pseudo-score tests for parameters summarizing categorical data. Such methods perform well, usually much better than inverting Wald tests. For some models ordinary score inferences are impractical, such as when the likelihood function is not an explicit function of the model parameters. For such cases, we propose pseudo-score inference based on a Pearson-type chi-squared statistic that compares fitted values for a working model with fitted values of the model when a parameter of interest takes a fixed value. For multinomial models, this interval simplifies to the large-sample score interval when the model is saturated but otherwise can be much simpler to construct. Possible generalizations of the method include a quasi-likelihood approach for discrete data. For small samples, `exact' methods are conservative inferentially, but inverting a score test using the mid-P value provides a sensible compromise. Finally, we briefly review a different pseudo-score approach that approximates the score interval for proportions and their differences with independent or dependent samples by adding pseudo data before forming simple Wald confidence intervals.
ABSTRACT: We consider inference from data matrices that have low dimensional mean structures. In educational testing and in probe-level microarray data, estimation and inference are often made from a single data matrix believed to have a uni-dimensional mean structure. In this talk, we focus on probe-level microarray data to examine the adequacy of a uni-dimensional summary for characterizing the data matrix of each probe-set. To do so, we propose a low-rank matrix model, and develop a useful framework for testing the adequacy of uni-dimensionality against targeted alternatives. We analyze the asymptotic properties of the proposed test statistics as the number of rows (or columns) of the data matrix tends to infinity, and use Monte Carlo simulations to assess their small sample performance. Applications of the proposed tests to GeneChip data show that evidence against a uni-dimensional model is often indicative of practically relevant features of a probe-set. The talk is based on joint work with Xingdong Feng, currently a postdoctoral fellow at the National Institute of Statistics Sciences.
ABSTRACT: None Given.
ABSTRACT: None Given.
ABSTRACT: None Given.
|
Click
here for past schedules |
Biostatistics
Webmaster |