Length of hospital stay was analyzed in Ile-de-France, for 1147 patients with drug poisoning, diabetes mellitus, head trauma, varicoses veins, urinary calculus, gall-stone disease, or myocardial infarction. The explanatory variables (socio-demographic, hospital, and clinical characteristics) were different from one diagnosis to another; the percentage of variance explained laid between 13% and 26%, depending on the specific diagnosis. Results confirm that length of stay is more than a managerial indicator; it also contains clinical-epidemiological information. Results from multiple linear regression, logistic regression, and Cox model were compared for diabetes mellitus and myocardial infarction. From a managerial point of view, logistic regression provided operational information, whereas results from multiple linear regression, as an explanatory method, were disappointing. Cox model was less interesting since there is not censoring data in this study population. The use of administrative data for research is discussed.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:QMM.60569 |
| Date | January 1991 |
| Creators | Medina, Sylvia |
| Publisher | McGill University |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | French |
| 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: 001243217, proquestno: AAIMM72164, Theses scanned by UMI/ProQuest. |
Page generated in 0.0017 seconds