Nested Frailty Cox Models with Time-Dependent Covariates: Application to Dairy Cow Data

• Activity Number: 648
• Type: Contributed
• Date/Time: Thursday, August 8, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Adel Elghafghuf*+ and Henrik Stryhn and Simon Dufour and Kristen Reyher and Ian Dohoo
• Companies: and University of Prince Edward Island and University of Montreal and University of Bristol and University of Prince Edward Island
• Keywords: survival data ; Cox model ; nested frailty ; simulation study ; time-dependent variables ; clinical mastitis

Abstract

The hierarchical survival data commonly found in veterinary observational studies are often large in size and contain important time-dependent variables and effects. In such cases, the typical data expansion into counting-process format leads to very large data sets, thus complicating the analysis and requiring excessive computing time. In this study, a nested frailty Cox model with time-dependent covariates was applied to Canadian Bovine Mastitis and Milk Quality Research Network data, where 10831 lactations within 8035 cows from 69 farms were followed through the lactation until the first case of clinical mastitis. The analysis shows substantial variation at both animal and farm levels. Further, a small simulation study for a setting similar to the real data compared two different analytical approaches.