Measurement Error in Nonlinear Models

Written by leading authorities in nonlinear regression modeling, Measurement Error in Nonlinear Models: A Modern Perspective, Second Edition provides an up-to-date overview of analysis strategies for regression models in which variables are measured with errors. Thoroughly revised, this second edition includes additional material on Bayesian methods and semiparametric regression and a new chapter on generalized linear mixed models. Focusing on general ideas and strategies of estimation and inference, the authors provide various detailed worked examples, computed using MATLAB and R, from the fields of epidemiology and biometry. Data sets and software for all of the examples are available for download from the Internet.

Introduction. Important Concepts. Linear Regression and Attenuation. Regression Calibration. Simulation Extrapolation. Instrumental Variables. Score Function Methods. Likelihood and Quasilikelihood. Bayesian Methods. Hypothesis Testing. Longitudinal Data and Mixed Models. Nonparametric Estimation. Semiparametric Regression. Survival Data. Response Variable Error. Appendix A: Background Material. Appendix B: Technical Details. References. Applications and Examples Index. Index.