Focusing on predictive or observable inference, the author highlights its advantages over traditional parametric inference. The text emphasizes the applications of the Bayesian approach in predictive analysis, showcasing methods that lack parametric counterparts. Through this exploration, the author offers insights into innovative statistical techniques that enhance predictive capabilities in various contexts.
A collection of refereed papers from a six-week workshop on statistics in the health sciences, that brought together theoretical and applied statisticians from universities, medical and public health schools, government and private institutions, and pharmaceutical companies involved in prediction problems in the life and social sciences and in diagnostic and screening tests. A number of papers with applications were presented and particularly lively discussions ensued involving the critical issues and difficulties in using and interpreting diagnostic tests and implementing mass screening programmes. The prediction or control of future events, such as survival, comparative survival and survival post intervention for a disease of even for certain biological of natural events was also represented by participants who presented work that devised predictive methodology for a variety of problems, mainly from a Bayesian perspective.