Garib Nath Singh

Assessment of Exponential Methods of Estimation Under Nonresponse in Two-Occasion Successive Sampling

This article deals with the problem of estimation of current population mean when nonresponse occurs on the current (second) occasion in two-occasion successive sampling. Using the subsampling of nonrespondent technique, exponential-type estimators of current population mean have been proposed and their properties are examined. Optimum replacement strategies for the proposed estimators have been suggested and empirical studies are carried out to assess the performances of the proposed estimators. Results are interpreted and suitable recommendations are made.

Estimation of Population Mean in Presence of Non Response in Two-Occasion Successive Sampling

The present work intended to emphasize the role of one varying auxiliary variable at both the occasions to improve the precision of estimates of population mean at current occasion in two-occasion successive sampling in presence of non-response. Two different efficient estimators are proposed and their theoretical properties are examined. The proposed estimators have been compared with (i) the sample mean estimator in the presence of non response, where no past information is used and (ii) the estimator suggested by Singh and Priyanka [1], which is a linear combination of the means of the matched and unmatched portions of the sample at the current occasion [1]. Theoretical results have been interpreted through empirical studies which are followed by suitable recommendations.

A Class of Exponential Regression Type Estimators for Population Variance in Two-Phase Sampling

This article deals with the problems of efficient estimation of population variance in two-phase (double) sampling. Using information on two auxiliary variables, a class of chain exponential to regression type estimators has been proposed and its properties are studied under two different structures of two-phase sampling. Superiority of suggested class of estimators over some existing ones is established through numerical illustrations. Suitable recommendations to the survey statistician are also made.