In stratified sampling, one can use the separate or combined ratio estimators. The authors in this paper limited to their combined ratio estimators. Kalidar and Cingi (Ref. 1) have introduced various combined ratio estimators by using transformations introduced by several authols such as Sisodia and Dwivedi (Ref. 2). Singh and Kakran (Ref. 3) and Upadhyaya and Singh (Ref. 4). Sisodia and Dwivedi (Ref. 2) proposed a ratio estimator Y_SD by using a transformation involving coefficient of variation (C_x) of an auxiliary variable X. Singh and Kakran (Ref. 3) proposed another ratio estimator Y_SK by using a transformation involving coefficient of kurtosis β_2(x) instead of coefficient of variation. Upadhyaya and Singh (Ref. 4) further modified these ratio estimators and suggested two estimators Y_USl and Y_US2 by using both C_x and β_2(x) Later Kalidar and Cingi (Ref. 1) used the aboveLmentioned estimators in stratified sampling in the form of a combined ratio estimator. They concluded that an ordinary combined ratio estimator is better than the transformed combined ratio estimators. The authors have given their proposed class of estimators in Section 2. Section 3 describes the efficiency of the proposed estimator with that of combined ratio estimators. Data and simulations results are presented in Section 4. Finally, conclusions are given in Section 5. (7 refs.)
展开▼