Volume no :17, Issue no: 1, March (2016)

EXTENSION OF INFORMATION CASES ON MIXTURE REGRESSION ESTIMATORS USING MULTI-AUXILIARY VARIABLES AND ATTRIBUTES IN TWO-PHASE SAMPLING

Author's: Peter I. Ogunyinka and A. A. Sodipo
Pages: [1] - [20]
Received Date: December 26, 2016
Submitted by:
DOI: http://dx.doi.org/10.18642/jsata_7100121754

Abstract

In survey sampling, auxiliary variables and attributes have been employed to reduce the mean square error (MSE) of estimators, hence, improving such estimators in two-phase sampling. Similarly, the three ways of utilizing auxiliary variables and attributes (full, partial, and no information cases) have provided flexibility in its usage. In this article, we have proposed two additional cases to the existing partial information case to make up five information cases of utilizing auxiliary variables and attributes. Similarly, schema of each of the proposed estimators were introduced for estimator formation. It was ascertained that partial information case II (PIC-II) and partial information case III (PIC-III) are efficient over partial information case I (PIC-I). Hence, the proposed two partial information cases (PIC-II and PIC-III) gained improved efficiency over the existing partial information case I (PIC-I).

Keywords

partial information case, mixture regression estimator, two-phase sampling, auxiliary variable, auxiliary attribute.