SIMULATION-EXTRAPOLATION ESTIMATION IN PARAMETRIC MEASUREMENT ERROR MODELS

We describe a simulation-based method of inference for parametric meas urement error models in which the measurement error variance is known or at least well estimated. The method entails adding additional measu rement error in known increments to the data, computing estimates from the contaminated data, establishing a trend between these estimates a nd the variance of the added errors, and extrapolating this trend back to the case of no measurement error. We show that the method is equiv alent or asymptotically equivalent to method-of-moments estimation in linear measurement error modeling. Simulation studies are presented sh owing that the method produces estimators that are nearly asymptotical ly unbiased and efficient in standard and nonstandard logistic regress ion models. An oversimplified but fairly accurate description of the m ethod is that it is method-of-moments estimation using Monte Carlo-der ived estimating equations.