Item non-response imputation in the Korea National Health and Nutrition Examination Survey (KNHANES)

Abstract

Objectives The Korea National Health and Nutrition Examination Survey (KNHANES) is a public health survey that assesses individual health and nutritional status and monitors the prevalence of major chronic diseases. In general, sampling weights are adjusted for unit non-responses and imputation for item non-responses. In this study, we proposed strategies for imputing item non-responses in the KNHANES in order to improve the usefulness of data, to minimize bias, and to increase statistical power.

Methods After applying some logical imputation, we adopted two separate imputation methods for each type of variables: unweighted sequential hot-deck imputation for categorical variables and sequential regression imputation for continuous variables. For variance estimation, multiple imputations were applied to the continuous variables. To evaluate the performance of the proposed strategies, we compared marginal distributions of imputed variables and the results multivariate regression analysis for the complete-case data and the expanded data with imputed values, respectively.

Results When comparing the marginal distributions, most of non-responses were imputed. The multivariable regression coefficients presented similar estimates; however, the standard errors decreased, resulting in a statistically significant P-values. Our evaluation shows that the proposed imputation strategies may cope with precision loss due to missing data, thus enhancing statistical power in the analysis of the KNHANES by providing expanded data with imputed values.

Conclusions The proposed imputation strategy may enhance utility of data by increasing the number of complete-cases in the analysis while distorting the original distribution, thus laying a foundation to cope with the occurrence of item non-response in further surveys.