• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.29-40
• /
• 2019

Categorical data with non-responses are frequently observed in election poll surveys, and can be represented by incomplete contingency tables. To estimate supporting rates of candidates, the identification of the missing mechanism should be pre-determined because the estimates of non-responses can be changed depending on the assumed missing mechanism. However, it has been shown that it is not possible to identify the missing mechanism when using observed data. To overcome this problem, sensitivity analysis has been suggested. The previously proposed sensitivity analysis can be applicable only to two-way incomplete contingency tables with binary variables. The previous sensitivity analysis is inappropriate to use since more than two of the factors such as region, gender, and age are usually considered in election poll surveys. In this paper, sensitivity analysis suitable to an multi-dimensional incomplete contingency table is devised, and also applied to the 19th Korean presidential election poll survey data. As a result, the intervals of estimates from the sensitivity analysis include actual results as well as estimates from various missing mechanisms. In addition, the properties of the missing mechanism that produce estimates nearest to actual election results are investigated.

• The Korean Journal of Applied Statistics
• /
• v.36 no.6
• /
• pp.547-559
• /
• 2023

Proper handling of nonresponse in sample survey improves the accuracy of the parameter estimation. Various studies have been conducted to properly handle MAR (missing at random) nonresponse or MCAR (missing completely at random) nonresponse. When nonresponse occurs, the PSA (propensity score adjusted) estimator is commonly used as a mean estimator. The PSA estimator is known to be unbiased when known sample weights and properly estimated response probabilities are used. However, for MNAR (missing not at random) nonresponse, which is affected by the value of the study variable, since it is very difficult to obtain accurate response probabilities, bias may occur in the PSA estimator. Chung and Shin (2017, 2022) proposed a post-stratification method to improve the accuracy of mean estimation when MNAR nonresponse occurs under a non-informative sample design. In this study, we propose a double post-stratification method to improve the accuracy of the naive PSA estimator for MNAR nonresponse under an informative sample design. In addition, we perform simulation studies to confirm the superiority of the proposed method.