Improvement on Calibration Weightings in Stratified Random Sampling

Abstract

Calibration weightings is the process of formulating calibration constraints using a given distance measure to obtain expression of the calibration weights. One of the major limitations of the simple calibration technique by Deville and Sarndal (1992); is that the calibration weights obtained by this process may be negative and or extremely large. To overcome this challenge, this study develops a new framework for obtaining optimum calibration weightings using inverse exponentiation.  A new calibration regression estimator of population mean is proposed in stratified random sampling. Properties of the new estimator are derived and its efficacy established through empirical comparisons with existing estimators. Results of analysis showed that the new estimator obtained by the new calibration weightings is more precise and highly efficient than calibration estimators obtained by the simple calibration technique by Deville and Sarndal (1992), under the same optimum conditions.

International Journal of Statistical Sciences, Vol. 24(2), November, 2024, pp 125-136