Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Time varying coefficient model for gap times in ecological momentary assessment data

Li, Xiaoxue (2015) Time varying coefficient model for gap times in ecological momentary assessment data. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Submitted Version

Download (761kB)

Abstract

Ecological momentary assessment (EMA) studies investigate instantaneous and repeated observations on subjects over time in their everyday life. Such study designs are useful for applications to public health and social sciences because they provide intensive information about the temporal pattern of one's behavior. Throughout this dissertation, we will use an EMA study of intermittent smokers (ITS) to demonstrate our method. In this EMA study,
events such as smoking are of primary interest. Here, we focus on a particular temporal pattern when smoking events are clustered in time. The distributions of the time-clusters or smoking "bouts" and covariates that predict such behavior are our interest. Traditional linear
mixed effects models are not typically equipped to properly assess this kind of investigation.
In this dissertation, we introduce a method of displaying the temporal behavior of subjects via functions of event gap times which allow us to easily identify bouts. We also apply an existing time-varying coefficient model to cumulative log gap times to characterize the time
patterns of smoking while concomitantly adjusting for behavioral covariates that may be time varying and related to smoking. The mixed effects model we consider here produces a linear function with coefficients that change over time and hence, can identify meaningful temporal
changes both at the subject and population levels. We also apply the inverse probability of weighting methods to weight the observed cases and handle missing data generated by the study design.

Our method has public health significance in that it allows one to identify time patterns (periodic or otherwise) in health event outcomes that can occur multiple times. Hence,
one can characterize the time trajectory of these multiply observed events and possibly develop interventions when necessary to alter the time course of such processes.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Li, Xiaoxuexil55@pitt.eduXIL55
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairAnderson, Stewart J.sja@pitt.eduSJA
Committee MemberWahed, Abdus Swahed@pitt.eduWAHED
Committee MemberYouk, Adayouk@pitt.eduYOUK
Committee MemberShiffman, Saulshiffman@pitt.eduSHIFFMAN
Date: 28 January 2015
Date Type: Publication
Defense Date: 17 October 2014
Approval Date: 28 January 2015
Submission Date: 23 November 2014
Access Restriction: 3 year -- Restrict access to University of Pittsburgh for a period of 3 years.
Number of Pages: 79
Institution: University of Pittsburgh
Schools and Programs: Graduate School of Public Health > Biostatistics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Ecological Momentary Assessment, Intensive Longitudinal Data, Recurrent Events Analysis, Time-varying Coefficient Model, Gap Times
Date Deposited: 28 Jan 2015 16:41
Last Modified: 01 Jan 2018 06:15
URI: http://d-scholarship.pitt.edu/id/eprint/23583

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item