A Study on New Methods of Ratio Exponential Type Imputation in Sample Surveys

Abstract

In this article, we have suggested new methods of ratio exponential type imputation and proposed their corresponding point estimators to deal with the problems of non-response in sample surveys for the prior outlay of an auxiliary variable x. The expression of the biases and their mean square errors of the proposed estimators have been derived, upto the first order of large sample approximation under SRSWOR scheme and compared with the mean method of imputation, ratio method of imputation, regression method of imputation and the estimators of Singh and Horn (Metrika

Product Exponential Method of Imputation in Sample Surveys

“…Following the Prasad (2016Prasad ( & 2017, a product exponential method of imputation and their corresponding estimator has suggested for estimating the population meanȲ in sample surveys. The suggested imputation method, After imputation, the data take the form:…”

On The Efficiency of Almost Unbiased Mean Imputation When Population Mean of Auxiliary Variable is UnknownOn The Efficiency of Almost Unbiased Mean Imputation When Population Mean of Auxiliary Variable is Unknown

“…Prasad [37] proposed ratio exponential imputation scheme given in (2.21) to address the problem of compromised in Singh et al [36] as…”

“…conducted by human are often characterized by non-response. Hansen and Hurwitz [24] first discussed the issue of non-response and imputation methods to deal with nonresponse issues were suggested by several scholars like Singh and Horn [25], Singh and Deo [26], Ahmed et al [27], Wang and Wang [28], Kadilar and Cingi [29], Toutenburg et al [30], Singh (2009), Diana and Perri [31], Al-Omari et al [32], Singh et al [33], Mishra et al [34], Singh and Gogoi [35], Singh et al [36], Prasad [37], Audu et al [38][39][40][41], Shahzad et al [42] and Audu and Singh [43] are some of the most recent imputation methods. However, some of the estimators of the schemes proposed by aforementioned authors are functions of population mean of auxiliary variable ( X ) and if X is unknown, the schemes can not be applied to real life situations and are biased.…”

Modified Compromized Type Method of Imputation for Estimating Population Mean

“…The problem of non-response has been considered by many authors including Singh and Horn (2000), Singh and Deo (2003), Wang and Wang (2006), Kadilar and Cingi (2008), Toutenburg et al (2008), Singh (2009), Diana and Perri (2010), Al-Omari et al (2013), Singh et al (2014), Gira (2015), Singh et al (2016), Singh, et al (2010), Bhushan and Pandey (2016) and Prasad (2017), Audu et al (2020a, b, c), Audu et al (2021). Singh and Deo (2003) and Prasad (2017) estimators converged to sample mean as the values of unknown parameters in their estimators converged to zero while Singh and Horn (2000), Singh et al (2014) estimators converged to sample mean as the values of unknown parameters converged to one. These converges lead to lose of information on the auxiliary variables which in turn reduces their efficiencies.…”