Search

Missing data is an obligatory phenomenon in most of the sample surveys and when it is not handled cautiously at beginning of the study, outcomes may result to substantial biases in the survey estimates. Retaining such evidences into cognizance, this paper proffers few possible improved imputation methods to figure out the problem of missing data at the starting of the study and proffers computation procedure of the population mean using simple random sampling. The characteristics of the proffered imputation methods are ascertained till first order approximation pursued by a computational study carried out using several existent and hypothetical data sets. The findings are turned out rather promising showing dominance over the existing imputation methods. Further, apposite advices have been forwarded to the survey professionals for practical applications. [ABSTRACT FROM AUTHOR]

Abstract In this paper, we intend to utilize the multi auxiliary information available under RSS for the imputation of missing data. The mean imputation, regression imputation methods, and power transformation imputation method are identified as special cases of the proposed imputation methods. These methods are dominated by the proposed imputation methods. The theoretical comparison provides the dominance conditions of the proposed imputation methods over their conventional counterparts. In support of the theoretical findings, a simulation study is considered over a hypothetically generated population. Furthermore, some real data examples are also provided to generalize the simulation results. [ABSTRACT FROM AUTHOR]

In this article, we propose additive shared gamma frailty model and additive shared inverse Gaussian frailty model with Lindley as baseline distribution to analyze the infectious disease data set of McGilchrist and Aisbett. The Bayesian approach of Markov Chain Monte Carlo technique was employed to estimate the parameters involved in the models. A simulation study was also carried out to compare the true values and estimated values of the parameters. Comparison of proposed models and the existing models was also done by using Bayesian information criteria such as BIC, WBIC and Bayes factor. A better model was also recommended for infectious disease data. [ABSTRACT FROM AUTHOR]

This paper introduces some improved methods of imputation using higher order moment of an auxiliary variable while imputing missing values. The performance of the proposed imputation methods are investigated relative to the methods proposed by Mohamed, Sedory, and Singh (2016) and Bhushan and Pandey (2016, 2018). A comparative study has been carried out and it has been shown that the proposed methods perform better in comparision to methods proposed by Mohamed, Sedory, and Singh (2016) and Bhushan and Pandey (2016, 2018). The theoretical findings are supported by numerical study on two real populations and a simulation study using hypothetical population. [ABSTRACT FROM AUTHOR]