Measurement error and misclassification in statistics and epidemiology. Impacts and Bayesian adjustments.

*(English)*Zbl 1039.62019Interdisciplinary Statistics Series. Boca Raton, FL: Chapman and Hall/CRC (ISBN 1-58488-335-9/hbk). xi, 188 p. $ 79.95; £ 52.99 (2004).

This book is concerned with statistical models that contain eplanatory variables that are mismeasured. The approach is Bayesian, and there are separate chapters for continuous and categorical explanatory variables. However, the author’s ambition is to draw the two topics together as much as possible.

The book is organised as follows. After the Introduction, there are two chapters titled “The Impact of Mismeasured Continuous Variables” and “The Impact of Mismeasured Categorical Variables”. Following that, there are two chapters on adjusting for mismeasurement in the two cases. In an appendix the author gives the main ideas of Bayesian analysis and Markov Chain Monte Carlo algorithms.

Reviewer: Göran Broström (Umea)