To evaluate why discordance may occur between regression coefficients from cross sectional and longitudinal analyses when ventilatory function is related to ageing, a population was created by computer, and modelled to simulate functional change during life. The program incorporated the effects of many factors known to influence lung function measurements, which were adjusted experimentally so that their contributions to any discordance could be assessed. Regression analyses showed that significant discordance could be induced if the oldest birth cohort failed to reach the same maximal level of function as the youngest; if a quadratic ageing term was excluded from the independent regression variables; or if the effects of certain confounders were present. Discordance occurred additionally if cross sectional estimates became imprecise, but then the differences (often marked) from longitudinal estimates were not significant. It is concluded that discordance may be fundamental and unavoidable (though explicable), or merely a consequence of imprecision.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:QMM.33000 |
| Date | January 2001 |
| Creators | Hendrick, David J. |
| Contributors | Becklake, M. R. (advisor), Hanley, J. A. (advisor) |
| Publisher | McGill University |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Format | application/pdf |
| Coverage | Master of Science (Department of Epidemiology and Biostatistics.) |
| Rights | All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated. |
| Relation | alephsysno: 001838365, proquestno: MQ75315, Theses scanned by UMI/ProQuest. |
Page generated in 0.002 seconds