Alexandria Digital Research Library

Nonparametric Mixed-Effects Density Regression

Author:
Chiu, Chi-Yang
Degree Grantor:
University of California, Santa Barbara. Statistics and Applied Probability
Degree Supervisor:
Yuedong Wang
Place of Publication:
[Santa Barbara, Calif.]
Publisher:
University of California, Santa Barbara
Creation Date:
2015
Issued Date:
2015
Topics:
Statistics
Keywords:
Mixed-Effects Model
Density Estimation
Genres:
Dissertations, Academic and Online resources
Dissertation:
Ph.D.--University of California, Santa Barbara, 2015
Description:

Conditional density provides the most informative summary of the relationship between independent and dependent variables. It enables us to examine the overall shapes of densities as well as summary characteristics such as quantiles and modes. Repeated measures designs are widely used in many areas such as agriculture, education and pharmaceutical sciences. The data from repeated measures designs are correlated. We develop a nonparametric method for conditional density estimation for repeated measures data. Specifically we propose nonparametric mixed-efffects density regression (NMDR) models. The NMDR models allow us to estimate conditional densities with fewer constraints on the form of densities when data are correlated. The models may be constructed using Smoothing Spline ANOVA (SS ANOVA) methods. Penalized marginal likelihood is used to estimate the density function as well as parameters. We use the stochastic approximation algorithm (SAA) with Newton-Raphson method for optimization, and Markov chain Monte Carlo (MCMC) for approximating integrals. An example from speech science is provided to illustrate the utility of our model.

Physical Description:
1 online resource (138 pages)
Format:
Text
Collection(s):
UCSB electronic theses and dissertations
ARK:
ark:/48907/f389141v
ISBN:
9781321695809
Catalog System Number:
990045119300203776
Rights:
Inc.icon only.dark In Copyright
Copyright Holder:
Chi-Yang Chiu
File Description
Access: Public access
Chiu_ucsb_0035D_12532.pdf pdf (Portable Document Format)