GROUP-BASED TRAJECTORY MODELING WITH BINARY AND ZERO-INFLATED COUNT OUTCOMES: APPLICATION TO GERIATRIC PNEUMONIA
| dc.contributor.advisor | Lim, Hyun J | |
| dc.contributor.committeeMember | Mondal, Prosanta | |
| dc.contributor.committeeMember | Szafron, Michael | |
| dc.contributor.committeeMember | Balbuena, Lloyd | |
| dc.creator | Kim, Min Young | |
| dc.date.accessioned | 2022-07-15T15:14:44Z | |
| dc.date.available | 2022-07-15T15:14:44Z | |
| dc.date.copyright | 2022 | |
| dc.date.created | 2022-07 | |
| dc.date.issued | 2022-07-15 | |
| dc.date.submitted | July 2022 | |
| dc.date.updated | 2022-07-15T15:14:44Z | |
| dc.description.abstract | A developmental trajectory is defined as an evolution of an outcome over age or time (Nagin, 2005). Several statistical approaches are available for trajectory analysis. Hierarchical modeling and latent growth curve modeling are most commonly used. However, this thesis is focused on widely used method, “Group-based trajectory modeling.” Group-based trajectory modeling (GBTM) is an application of finite mixture modeling that the population is composed of distinct groups, each with a different underlying trajectory and every subject in the group approximately follows the same patterns of behavior of outcome over age or time (Nagin, 1999). This thesis utilized the Korean Health Panel Study, which included 4007 individuals 65 years old or older at the baseline. Trajectory analysis was conducted with GBTM for geriatric pneumonia with binary and count outcomes. The models were compared and the binary outcome trajectory model was considered a better fit model. Both the binary outcome trajectory model and the zero-inflated count outcome trajectory model identified three trajectory groups with similar shapes: “low-flat,” “low-to-high,” and “high-to-low.” The majority of the participants belonged to the “low-flat” group. In the binary outcome trajectory model, having three household members, having a disability, and having a chronic respiratory disease were significant risk factors for the pneumonia trajectory groups. In the zero-inflated count outcome trajectory model, being male and having a chronic respiratory disease were the significant risk factors. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | https://hdl.handle.net/10388/14035 | |
| dc.language.iso | en | |
| dc.subject | Group-based trajectory modeling | |
| dc.subject | geriatric pneumonia | |
| dc.title | GROUP-BASED TRAJECTORY MODELING WITH BINARY AND ZERO-INFLATED COUNT OUTCOMES: APPLICATION TO GERIATRIC PNEUMONIA | |
| dc.type | Thesis | |
| dc.type.material | text | |
| thesis.degree.department | School of Public Health | |
| thesis.degree.discipline | Biostatistics | |
| thesis.degree.grantor | University of Saskatchewan | |
| thesis.degree.level | Masters | |
| thesis.degree.name | Master of Science (M.Sc.) |