Abstract
Although deletion of cases is still a common method of dealing with item nonresponse, imputation is a major alternative. With traditional methods of imputation, though, the usual variance formulas understate the variance of estimates. This paper proposes that items be imputed from distributions more diffuse than those of the real data, thereby compensating for the underestimation of variance by the usual formulas. The impact on covariances is considered in the design of the method. The method is intended for use by data analysts applying techniques based on functions of first and second moments of means only.
Highlights
1.1 Item nonresponseMost surveys have item nonresponse no matter how well planned they may be
The objective of this paper is to explore methods of imputation that permit the use of standard variance formulas
An improvement on mean imputation, this approach is doomed to failure when it comes to estimation of variances as we shall see
Summary
Most surveys have item nonresponse no matter how well planned they may be These missing data become a problem when it comes time to analyze the dataset. In another analysis, x is analyzed in conjunction with z instead, the estimated mean of x will in general be based on different cases so we get two different estimates of the same quantity These inconsistencies can be very confusing to careful readers, resulting in a loss of confidence in the research. One can use complete data methods of analysis without any need to discard cases. Another advantage is that the data can be imputed “in house,” bringing the additional knowledge of the data collection people to bear on the missing data problem. For general discussion of imputation, we recommend Kalton (1983), Kalton and Kasprzyk (1986), and Rubin (1987)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.