<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T18:21:15Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/5813" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/5813</identifier><datestamp>2017-03-21T20:28:46Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9934</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="e943eea9-2caf-4597-8a60-d431ea3db729" confidence="600">Ahmed, Muhamad Rashid</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2011-03-09T19:44:21Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2011-03-09T19:44:21Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2011-03-09T19:44:21Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2011</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/5813</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Hierarchical models are applicable to modeling data from complex&#xd;
surveys or longitudinal data when a clustered or multistage sample&#xd;
design is employed. The focus of this thesis is to investigate&#xd;
inference for discrete hierarchical models in the presence of&#xd;
missing data. This thesis is divided into two parts: in the first&#xd;
part, methods are developed to analyze the discrete and ordinal&#xd;
response data from hierarchical longitudinal studies. Several&#xd;
approximation methods have been developed to estimate the parameters&#xd;
for the fixed and random effects in the context of generalized&#xd;
linear models. The thesis focuses on two likelihood-based&#xd;
estimation procedures, the pseudo likelihood (PL) method and the adaptive&#xd;
Gaussian quadrature (AGQ) method.&#xd;
&#xd;
The simulation results suggest that AGQ&#xd;
is preferable to PL when the&#xd;
goal is to estimate the variance of the random intercept in a&#xd;
complex hierarchical model. AGQ provides smaller biases&#xd;
for the estimate of the variance of the random intercept.&#xd;
Furthermore, it permits greater&#xd;
flexibility in accommodating user-defined likelihood functions.&#xd;
&#xd;
In the second part, simulated data are used to develop a method for&#xd;
modeling longitudinal binary data when non-response depends on&#xd;
unobserved responses. This simulation study modeled three-level&#xd;
discrete hierarchical data with 30% and 40% missing data&#xd;
using a missing not at random (MNAR) missing-data mechanism. It&#xd;
focused on a monotone missing data-pattern. The imputation methods&#xd;
used in this thesis are: complete case analysis (CCA), last&#xd;
observation carried forward (LOCF), available case missing value&#xd;
(ACMVPM) restriction, complete case missing value (CCMVPM)&#xd;
restriction,  neighboring case missing value (NCMVPM) restriction,&#xd;
selection model with predictive mean matching method (SMPM), and&#xd;
Bayesian pattern mixture model. All three restriction methods and&#xd;
the selection model used the predictive mean matching method to&#xd;
impute missing data. Multiple imputation is used to impute the&#xd;
missing values. These m imputed values for each missing data&#xd;
produce m complete datasets. Each dataset is analyzed and the&#xd;
parameters are estimated. The results from the m analyses are then&#xd;
combined using the method of Rubin(1987), and inferences are&#xd;
made from these results. Our results suggest that restriction&#xd;
methods provide results that are superior to those of other methods.&#xd;
The selection model provides smaller biases than the LOCF methods&#xd;
but as the proportion of missing data increases the selection model&#xd;
is not better than LOCF. Among the three restriction methods the&#xd;
ACMVPM method performs best. The proposed method provides an&#xd;
alternative to standard selection and pattern-mixture modeling&#xd;
frameworks when data are not missing at random. This method is&#xd;
applied to data from the third Waterloo Smoking Project, a&#xd;
seven-year smoking prevention study having substantial non-response&#xd;
due to loss-to-follow-up.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Missing Data</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">multilevel Model</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">Statistics (Biostatistics)</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">An Investigation of Methods for Missing Data in Hierarchical Models for Discrete Data</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending" lang="en">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Statistics and Actuarial Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>