Randomized response models deal with stigmatizing variables appearing in health surveys. Additive and subtractive scrambling in split sample and double response yield unbiased mean and sensitivity estimators of high precision. The split sample method is protective of privacy. The double response method is as protective only conditionally. To achieve the maximum efficiency, the scrambling variables must be similar to each other and the probability of obtaining a true response must be as large as possible. The randomized response procedures yield more efficient estimates of the average total number of classes missed by university students.

The improved classes of difference-type estimators of finite population median by using auxiliary information in simple random sampling and two-phase sampling have been proposed. The expressions for bias and mean square error are derived up to first order of approximation. Efficiency conditions and numerical comparisons reveal that the proposed class of estimators performs better than the other estimators under same scenario. Using fixed cost the optimum values are obtained for the two-phase sampling scheme.

This paper addresses the problem of estimating the population proportion π S possessing the sensitive attribute using stratified random sampling. Two alternatives to Kim and Warde [12] stratified randomized response model have been proposed. The prop