• Proceedings of the Korean Association for Survey Research Conference
• /
• 2000.06a
• /
• pp.1-14
• /
• 2000

We consider statistical methods for nonresponse problem in social and economic sample surveys. To create a complete data set, which does not include item nonresponse data, imputation methods are generally used. In this paper, we introduce some imputation methods and compare them with one another. Also, we consider some problems, which occur when an imputed data set is treated as a response data set. Due to the imputed values, the true variance of the estimator after imputation is increased by the imputation variance. However, since usual naive variance estimator constructed from the imputed data set does not estimate the imputation variance, the true variance of the estimator after imputation tends to be underestimated. Theoretical reason is investigated and serious results are explained through a simulation study. Finally, some adjusted variance estimation methods to compensate for underestimation are presented and discussed.

• Survey Research
• /
• v.1 no.2
• /
• pp.1-14
• /
• 2000

We consider statistical methods for nonresponse problem in social and economic sample surveys. To create a complete data set, which does not include item nonresponse data, imputation methods are generally used. In this paper, we introduce some imputation methods and compare them with one another. Also, we consider some problems, which occur when an imputed data set is treated as a response data set. Due to the imputed values, the true variance of the estimator after imputation is increased by the imputation variance. However, since usual naive variance estimator constructed from the imputed data set does not estimate the imputation variance, the true variance of the estimator after imputation tends to be underestimated. Theoretical reason is investigated and serious results are explained through a simulation study. Finally, some adjusted variance estimation methods to compensate for underestimation are presented and discussed.

• Proceedings of the Korean Statistical Society Conference
• /
• 2001.11a
• /
• pp.63-68
• /
• 2001

조사과정에서 필연적으로 발생하는 무응답을 보정하기 위해 보조정보를 사용한다. 이 때, 이용 가능한 보조정보의 차원이 크면, 계산과정에서 많은 시간이 소요되며 데이터를 다루기가 매우 어렵다. 또한 추정량의 분산이 보조정보의 차원에 의존하기 때문에 과소추정의 문제가 발생한다. 이러한 문제를 해결하기 위해 무응답 보정에서 적절한 보조정보의 선택 방법을 제안하였고, 이에 대한 효율성을 모의실험을 통해 살펴보았다.

• 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.

• Survey Research
• /
• v.11 no.1
• /
• pp.1-18
• /
• 2010

We compare various imputation methods for compensating wave nonresponse that are commonly adopted in many panel surveys. Unlike the cross-sectional survey, the panel survey is involved a time-effect in nonresponse in a sense that nonresponse may happen for some but not all waves. Thus, responses in neighboring waves can be used as powerful predictors for imputing wave nonresponse such as in longitudinal regression imputation, carry-over imputation, nearest neighborhood regression imputation and row-column imputation method. For comparison, we carry out a simulation study on a few income data from the Korean Welfare Panel Study based on two performance criteria: predictive accuracy and estimation accuracy. Our simulation shows that the ratio and row-column imputation methods are much more effective in terms of both criteria. Regression, longitudinal regression and carry-over imputation methods performed better in predictive accuracy, but less in estimation accuracy. On the other hand, nearest neighborhood, nearest neighbor regression and hot-deck imputation show higher performance in estimation accuracy but lower predictive accuracy. Finally, the mean imputation shows much lower performance in both criteria.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.227-231
• /
• 2005

민감한 모집단의 모수 추정 방법으로 확률화응답기법과 무응답을 고려한 직접조사 방법의 효율성을 비교 분석하였다.

• Communications for Statistical Applications and Methods
• /
• v.18 no.3
• /
• pp.367-376
• /
• 2011

BLS weight adjustment is a widely used method for business surveys with non-responses and outliers. Recent surveys show that the non-response weight adjustment of the BLS method is the same as the ratio imputation method. In this paper, we suggested a modified BLS weight adjustment method by imputing missing values instead of using weight adjustment for non-response. Monthly labor survey data is used for a small Monte-Carlo simulation and we conclude that the suggested method is superior to the original BLS weight adjustment method.

• The Korean Journal of Applied Statistics
• /
• v.30 no.3
• /
• pp.377-390
• /
• 2017

When conducting a survey, item nonresponse occurs if the respondent does not respond to some items. Since analysis based only on completely observed data may cause biased results, imputation is often conducted to analyze data in its complete form. The panel study is a survey method that examines changes of responses over time. In panel studies, there has been a preference for using information from response values of previous waves when the imputation of item nonresponses is performed; however, limited research has been conducted to support this preference. Therefore, this study compares the performance of imputation methods according to whether or not information from previous waves is utilized in the panel study. Among imputation methods that utilize information from previous responses, we consider ratio imputation, imputation based on the linear mixed model, and imputation based on the Bayesian linear mixed model approach. We compare the results from these methods against the results of methods that do not use information from previous responses, such as mean imputation and hot deck imputation. Simulation results show that imputation based on the Bayesian linear mixed model performs best and yields small biases and high coverage rates of the 95% confidence interval even at higher nonresponse rates.

• Environmental and Resource Economics Review
• /
• v.7 no.2
• /
• pp.31-51
• /
• 1998

우편설문조사를 이용한 조건부가치측정법을 통해 자료를 수집할 경우 무응답자의 발생은 보편적이며, 그러한 무응답자의 존재는 무응답자편의(無應答者偏倚) 가능성을 내재하고 있으므로, 표본의 통계치를 이용한 모집단에 대한 확대 적용을 위해서는 우선적으로 무응답자편의(無應答者偏倚)에 대한 검정(檢定)이 이루어져야 하며. 또한 무응답자편의(無應答者偏倚) 발생시 이에 대한 적절한 조치가 취해져야 한다. 본 연구에서는 다단계 우편설문발송법을 통해 수집된 자료를 이용하여 효과적인 무응답자편의(無應答者偏倚) 검정(檢定)의 수행과 무응답자군(無應答者群)의 평균지불의사액을 별도로 추정한 후 이를 이용하여 보다 합리적이고 정확한 총지불의사액(Aggregate WTP)의 도출방법을 제시하였다. 이는 우선적으로 무응답자편의(無應答者偏倚)를 분산분석을 통해 검정(檢定)한 후 선형외삽법으로 무응답자군(無應答者群)의 평균지불의사액을 추정하여 이를 모집단의 총지불의사액을 산출하는데 이용하는 방법으로 기존의 보수적인 방법들보다 상대적으로 저렴한 비용으로 무응답자편의(無應答者偏倚) 검정(檢定)을 가능하게 하며, 사회적 또는 인구특성상의 차이를 이용한 통계적 가중치 이용방법과는 달리 연구자의 직접적인 관심의 대상이 되는 지불의사액을 이용하여 무응답자편의(無應答者偏倚) 테스트를 하고 또한 무응답자군(無應答者群)의 평균지불의사액을 추정하여 보다 효율적이며 타당성이 있는 총지불의사액을 산출해 낼 수 있다는 장점이 있다.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2000.06a
• /
• pp.105-112
• /
• 2000

대부분 통계조사에서 흔히 발생하는 무응답을 처리하기 위한 방법으로 최근에는 표본 대체 방법이 널리 이용되고 있다. 본 논문에서는 여러 가지 표본 대체 방법을 소개하고 각 방법의 장. 단점을 비교. 설명한다. 그리고 대체된 데이터를 응답 데이터인 것처럼 활용했을 때 발생하는 문제점들을 지적하고 모의 실험을 통하여 그 정도를 살펴본다. 이와 더불어 제기된 문제점을 해결하는 몇 가지 해결방안을 소개한다.