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

The Latent Group-Based Trajectory Model: Development of Discrimination Measures and Joint Modeling with Subdistributions

Shah, Nilesh H. (2012) The Latent Group-Based Trajectory Model: Development of Discrimination Measures and Joint Modeling with Subdistributions. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

Primary Text

Download (701kB) | Preview


In clinical research, patient care decisions are often easier to make if patients are classified into a manageable number of groups based on homogeneous risk patterns. Investigators can use latent group-based trajectory models to estimate the posterior probabilities that an individual will be classified into a particular group of risk patterns. Although this method is increasingly used in clinical research, there is currently no measure that can be used to determine whether an individual's group assignment has a high level of discrimination. We propose a discrimination index and provide confidence intervals of the probability of the assigned group for each individual. We also propose a modified form of entropy to measure discrimination. Additionally, when analyzing research involving disease processes, many researchers are interested in estimating the effect of longitudinally measured biomarkers on the event time outcomes in the presence of competing risks. We propose a method to estimate this effect under the joint modeling framework. The proposed joint model involves three submodels: the first one models the latent risk trajectory groups; the second one models the longitudinal pattern of biomarkers conditional on a specific risk group; and the third one models the subdistribution function conditional on a specific risk group.

These methods are significant to public health research since they enable researchers to more confidently assign individual patients to risk groups based on their clinical measurements. The joint model also enables researchers to discover these distinct risk patterns more accurately by using patients' longitudinal data together with event time outcomes, while also adjusting for competing events.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Shah, Nilesh H.nhs3@pitt.eduNHS3
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairChang, Chung-Chou H.changj@pitt.eduCHANGJ
Committee MemberWeissfeld, Lisa Alweis@pitt.eduLWEIS
Committee MemberJeong, Jongjeong@nsabp.pitt.eduJJEONG
Committee MemberMoses-Kolko, EydiemosesEL@upmc.eduEMOSES
Date: 24 September 2012
Date Type: Completion
Defense Date: 18 July 2012
Approval Date: 24 September 2012
Submission Date: 23 July 2012
Access Restriction: 5 year -- Restrict access to University of Pittsburgh for a period of 5 years.
Number of Pages: 110
Institution: University of Pittsburgh
Schools and Programs: School of Public Health > Biostatistics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: latent class modeling, longitudinal data, finite mixture models, survival analysis
Date Deposited: 24 Sep 2012 16:03
Last Modified: 24 Sep 2017 05:15

Available Versions of this Item

  • The Latent Group-Based Trajectory Model: Development of Discrimination Measures and Joint Modeling with Subdistributions. (deposited 24 Sep 2012 16:03) [Currently Displayed]


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item