Mem squared error estimation in finite populations under nonlinear models |
| |
Authors: | Richard Valliant |
| |
Affiliation: | U.S. Bureau of Labor Statistics , Washington, DC, 20212 |
| |
Abstract: | Four estimators of the prediction mean squared error (MSB) of an estimated finite population total for a zero-one characteristic are examined. The characteristic associated with each population unit is modeled as the realization of a Bernoulli random variable whose expected value is a nonlinear function of a parameter vector and a set of known auxiliary variables. To compare the estimators, a simulation study is conducted using a population of hospitals. The MSB estimator Implied by the form of the assumed model underestimates the mean squared error in each of the cases studied and produces confidence lntervals with less than the nominal coverage probabilities. Of the three alternative MSE estimators presented, a linear approximation to the jackknife produces the best results and improves upon the model-specific estimator. |
| |
Keywords: | Bernoulli model confidence interval jackknife logistic regresssion prediction theory superpopulation model |
|
|