Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
417716 | Computational Statistics & Data Analysis | 2011 | 14 Pages |
The estimation of quantiles in the presence of auxiliary information is discussed. Calibration and poststratification techniques provide simple and practical procedures for incorporating auxiliary information into the estimation of distribution functions, which can offer some useful gains in efficiency. The estimator proposed combines these techniques and possesses a number of desirable properties, including yielding a genuine distribution function, providing simplicity of computation and generalizing Silva and Skinner’s estimator. This proposed procedure is compared to alternative methods. On the basis of simulation studies, the proposed post-stratified calibration estimator presents a good level of performance and comprises a valid alternative to other estimators of the distribution function.