Premium
A REGRESSION‐ TYPE ESTIMATOR IN SAMPLING WITH PPS AND WITH REPLACEMENT
Author(s) -
Tripathi T. P.
Publication year - 1969
Publication title -
australian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 0004-9581
DOI - 10.1111/j.1467-842x.1969.tb00101.x
Subject(s) - estimator , statistics , mathematics , bias of an estimator , consistent estimator , simple random sample , efficient estimator , ratio estimator , minimum variance unbiased estimator , trimmed estimator , population , medicine , environmental health
Summary A regression‐type estimator is proposed for the population total of a character y , when sample‐units are selected with probability proportional to some measure of size z (pps) and with replacement; and the information on yet another variate x is used. The proposed estimator is shown to be superior to the well‐known estimator (pps with replacement), and the ratio estimator (pps with replacement). It is also shown to be superior to the simple random estimator under some general conditions.