Photo by tamiminaser from unsplash
Abstract Stratification provides a powerful tool for improving the efficiency and, being suitable for various sampling situations, it is commonly used in practice. Motivated by the utility of stratified sampling… Click to show full abstract
Abstract Stratification provides a powerful tool for improving the efficiency and, being suitable for various sampling situations, it is commonly used in practice. Motivated by the utility of stratified sampling scheme, we focus on studying behavior of the estimator of proportion of a sensitive attribute while dealing with non-identical Bernoulli trials in survey research. The objective is achieved by considering a general randomized response model. Relative efficiency comparisons are presented along with cost analysis by considering different cost functions. Stratified random sampling is observed to be yielding more precise estimators.
Journal Title: Communications in Statistics - Theory and Methods
Year Published: 2018
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!