ERA

Download the full-sized PDF of COMPARISON OF DISCRETE DATA METHODS FOR REPEATED MEASURES DATA WITH SMALL SAMPLESDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R3XK85190

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

COMPARISON OF DISCRETE DATA METHODS FOR REPEATED MEASURES DATA WITH SMALL SAMPLES Open Access

Descriptions

Other title
Subject/Keyword
Discrete Data
Repeated Measures
Non-linear Mixed Effects Model
GEE
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Zhang, Xuechen
Supervisor and department
Carriere Chough, Keumhee (Department of Mathematical and Statistical Sciences)
Examining committee member and department
Prasad, N.G.N. (Department of Mathematical and Statistical Sciences)
Lele, Subhash R. (Department of Mathematical and Statistical Sciences)
Dinu, Irina (Department of Public Health Sciences)
Carriere Chough, Keumhee (Department of Mathematical and Statistical Sciences)
Department
Department of Mathematical and Statistical Sciences
Specialization
Biostatistics
Date accepted
2013-08-29T11:57:51Z
Graduation date
2013-11
Degree
Master of Science
Degree level
Master's
Abstract
Various analytical methods are available to analyze repeated measures data for both continuous and discrete data. In the case of discrete data, most methods are based on the assumption of asymptotic normality, requiring large samples. Naturally, their small sample performance may not match the expectation satisfactorily. Two main methods, the non-linear mixed effects (NLME) model and the generalized estimating equations (GEE) method, are investigated for their small sample performance on repeated binary data. We generated binary data, considering two levels of correlation at rho=0.3 and 0.7, with three cases of repeated measures with T=2, 4, or 6 and sample sizes ranging from 40 to 200. The two analysis methods are applied to each data set in 5000 simulations, and the resulting empirical size and power are compared. We conclude that the GEE performs quite well in small samples with satisfactory empirical size and statistical power and is therefore recommended.
Language
English
DOI
doi:10.7939/R3XK85190
Rights
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
2014-05-02T17:53:57.425+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 470022
Last modified: 2015:10:12 20:55:17-06:00
Filename: Zhang_Xuechen_Fall 2013.pdf
Original checksum: b55cbe58bcab04f906a8071a88617dd4
Well formed: true
Valid: true
File title: �������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������...
File title: Comparison of discrete data methods for repeated measures data with small samples
File author: Xuechen Zhang
Page count: 67
Activity of users you follow
User Activity Date