Sample size calculations for Bayesian prediction of bovine viral-diarrhoea-virus infection in beef herds.

We used a Bayesian classification approach to predict the bovine viral-diarrhoea-virus infection status of a herd when the prevalence of persistently infected animals in such herds is very small (e.g. <1%). An example of the approach is presented using data on beef herds in Wyoming, USA. The approach uses past covariate information (serum-neutralization titres collected on animals in 16 herds) within a predictive model for classification of a future observable herd. Simulations to estimate misclassification probabilities for different misclassification costs and prevalences of infected herds can be used as a guide to the sample size needed for classification of a future herd.

Survival and hazard functions for progressive diseases using saddlepoint approximations.

Saddlepoint approximations for the computation of survival and hazard functions are introduced in the context of parametric survival analysis. Although these approximations are computationally fast, accurate, and relatively straightforward to implement, their use in survival analysis has been lacking. We approximate survival functions using the Lugannani and Rice saddlepoint approximation to the distribution function or by numerically integrating the saddlepoint density approximation. The hazard function is approximated using the saddlepoint density and distribution functions. The approximations are especially useful for consideration of survival and hazard functions for waiting times in complicated models. Examples include total or partial waiting times for a disease that progresses through various stages (convolutions of distributions).