Abstract

  Introduction: Wide verity of causes of death exist in ageing societies. It is suitable to apply competing risk models in order to investigate and analyze time to death in the target population. The aim of this study was to identify some factors effective on survival of the elderly living in nursing home using Copula Competing Risk Model with Bayesian approach.

  Materials & Methods: In a descriptive-longitudinal study, data were collected from 510 elderly’s medical documents in Kashan Golabchi elderly nursing home. To identify effective factors associated with time to death of the elderly, medical diagnosis of cause of death cited in elderly’s documents were considered. Later, Competing Risk Model using Clayton Copula Function based on Bayesian approach was fitted and Credible intervals were estimated. To analyze the data WinBugs Software was used.

  Findings: In univariate analysis, being in the age at the beginning of reception, hypertension, family history of cardiovascular diseases, history of myocardial infarction, history of stroke were significant for time to death due to cardiovascular diseases in the elderly. In multivariate analysis, age group 75 to 90 years at the beginning of the reception (HR=2.1 CI 95%= (1.26, 3.67)) and history of stroke (HR=2 CI 95%= (1.28, 3.32)) were significant for time to death due to cardiovascular diseases in the elderly.

  Conclusion : One of the benefits of statistical modeling is the ability to generalize its results. According to the results, some crucial factors accelerating the time of death in elderly were identified. Therefore, it is highly recommended that, in therapeutic and preventive actions in order to increase the survival time for the elderly the significant studied factors should be considered.