• 응용통계연구
• /
• 제22권3호
• /
• pp.607-616
• /
• 2009

In many epidemiological studies, the occurrence times of the event of interest are right-censored or interval censored. In certain situations such as the AIDS data, however, the incubation period which is the time between HIV infection and the diagnosis of AIDS is usually doubly censored. In this paper, we impute the interval censored HIV infection time using three imputation methods. Mid imputation, conditional mean imputation and approximate Bayesian bootstrap are implemented to obtain right censored data, and then Gibbs sampler is used to estimate the coefficient factor of the incubation period. By using Bayesian approach, flexible modeling and the use of prior information is available. We applied both parametric and semi-parametric methods for estimating the effect of the covariate and compared the imputation results incorporating prior information for the covariate effects.

• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.577-587
• /
• 2023

Conventional categorical data imputation techniques, such as mode imputation, often encounter issues related to overestimation. If the variable has too many categories, multinomial logistic regression imputation method may be impossible due to computational limitations. To rectify these limitations, we propose a two-stage imputation method. During the first stage, we utilize the Boruta variable selection method on the complete dataset to identify significant variables for the target categorical variable. Then, in the second stage, we use the important variables for the target categorical variable for logistic regression to impute missing data in binary variables, polytomous regression to impute missing data in categorical variables, and predictive mean matching to impute missing data in quantitative variables. Through analysis of both asymmetric and non-normal simulated and real data, we demonstrate that the two-stage imputation method outperforms imputation methods lacking variable selection, as evidenced by accuracy measures. During the analysis of real survey data, we also demonstrate that our suggested two-stage imputation method surpasses the current imputation approach in terms of accuracy.

• 응용통계연구
• /
• 제21권1호
• /
• pp.95-107
• /
• 2008

농촌생활지표조사는 2000년부터 농촌자원개발연구소에서 매년 실시하는 조사로서 통계청 승인통계이다. 본 연구에서는 2005년 농촌생활지표조사에 사용된 원자료를 이용하였다. 원자료에 대한 에디팅 과정을 거친 후 무응답이 포함된 개체를 제거하여 얻어진 1,582 가구를 대 상으로 하였으며 총 146문항 중에서 최종 선택되어진 15문항을 증심으로 무응답 대체를 실시하였다. 실험에 사용된 대체법과 각 대체법의 효율성은 자료의 종류에 따라 다르게 적용되었다. 먼저 연속형 자료에 대해서는 평균대체, 회귀대체, 수정된 그레이 기반 k-NN 대체(DU, DW, WU, WW) 방법을 사용하여 무응답을 대체하고 RMSB를 이용하여 실험결과를 비교하였으며, 범주형 자료에 대해서는 최빈값 이용, 확률 대체, 조건부 최빈간 이용, 조건부 학률 대체, 단순 임의 핫덱 대체 방법을 사용하여 무응답을 대체하고 정확도(Accuracy)를 이용하여 실험 결과를 비교하였다. 실험 결과에 의하면 연속형 자료에 대해서는 회귀대체 또는 그레이 기반 k-NN 대체가 적절하고, 범주형 자료에 대해서는 핫덱 대체가 가장 적절한 것으로 나타났다.

• Communications for Statistical Applications and Methods
• /
• 제16권2호
• /
• pp.317-323
• /
• 2009

Recently not even government polices but small town decisions are based on the survey data/information, so the most of government agencies/organizations demand various sample surveys in each fields for more detail information. However in conducting the sample survey, nonresponse problem rises very often and it becomes a major issue on judging the accuracy of survey. For that matters, one solution ran be using the administration data. However unfortunately most of administration data are restricted to the common users. The other solution can be the imputation. Therefore several method, of imputation are studied in various fields. In this study, in stead of the simple regression imputation method which is commonly used, factor score regression method is applied specially to the incomplete data which have the unit and item misting values in survey data. Here for simulation study, Consumer Expenditure Surveys in Korea are used.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.633-650
• /
• 2013

All the imputation techniques proposed so far in literature for data imputation are offline techniques as they require a number of iterations to learn the characteristics of data during training and they also consume a lot of computational time. Hence, these techniques are not suitable for applications that require the imputation to be performed on demand and near real-time. The paper proposes a computational intelligence based architecture for online data imputation and extended versions of an existing offline data imputation method as well. The proposed online imputation technique has 2 stages. In stage 1, Evolving Clustering Method (ECM) is used to replace the missing values with cluster centers, as part of the local learning strategy. Stage 2 refines the resultant approximate values using a General Regression Neural Network (GRNN) as part of the global approximation strategy. We also propose extended versions of an existing offline imputation technique. The offline imputation techniques employ K-Means or K-Medoids and Multi Layer Perceptron (MLP)or GRNN in Stage-1and Stage-2respectively. Several experiments were conducted on 8benchmark datasets and 4 bank related datasets to assess the effectiveness of the proposed online and offline imputation techniques. In terms of Mean Absolute Percentage Error (MAPE), the results indicate that the difference between the proposed best offline imputation method viz., K-Medoids+GRNN and the proposed online imputation method viz., ECM+GRNN is statistically insignificant at a 1% level of significance. Consequently, the proposed online technique, being less expensive and faster, can be employed for imputation instead of the existing and proposed offline imputation techniques. This is the significant outcome of the study. Furthermore, GRNN in stage-2 uniformly reduced MAPE values in both offline and online imputation methods on all datasets.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.603-608
• /
• 2024

무응답 및 결측값은 표본 탈락, 설문조사에 대한 답변 회피 등으로 발생하며 정보의 손실 및 편향된 추론의 가능성이 있는 문제가 발생하게 되며, 이 경우 결측값을 적절한 값으로 바꾸는 대체가 필요하게 된다. 본 논문에서는 결측값에 대한 대체 방법으로 제안되었던 평균 대체, 다중회귀 대체, 랜덤 포레스트 대체, K-최근접 이웃 대체, 그리고 딥러닝을 기본으로 한 오토인코더 대체와 잡음제거 오토인코더 대체 방법을 비교한다. 결측값을 대체하는 이러한 방법들에 대해 설명하고, 연속형의 모의실험 데이터와 실제 데이터에 접목시켜 각 방법들을 비교하였다. 비교 결과 대부분의 경우에서 다중 대체 방법인 랜덤 포레스트 대체 방법과 잡음제거 오토인코더 대체 방법의 성능이 좋았음을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.421-436
• /
• 2006

Huang proposed a grey-based nearest neighbor approach to predict accurately missing attribute value in 2004. Our study proposes which way to decide the number of nearest neighbors using not only the deng's grey relational grade but also the wen's grey relational grade. Besides, our study uses not an arithmetic(unweighted) mean but a weighted one. Also, GRG is used by a weighted value when we impute missing values. There are four different methods - DU, DW, WU, WW. The performance of WW(Wen's GRG & weighted mean) method is the best of any other methods. It had been proven by Huang that his method was much better than mean imputation method and multiple imputation method. The performance of our study is far superior to that of Huang.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2006년도 PROCEEDINGS OF JOINT CONFERENCEOF KDISS AND KDAS
• /
• pp.55-62
• /
• 2006

Huang proposed a grey-based nearest neighbor approach to predict accurately missing attribute value in 2004. Our study proposes which way to decide the number of nearest neighbors using not only the dong's grey relational grade but also the wen's grey relational grade. Besides, our study uses not an arithmetic(unweighted) mean but a weighted one. Also, GRG is used by a weighted value when we impute a missing values. There are four different methods - DU, DW, WU, WW. The performance of WW(wen's GRG & weighted mean) method is the best of my other methods. It had been proven by Huang that his method was much better than mean imputation method and multiple imputation method. The performance of our study is far superior to that of Huang.

• 한국조사연구학회지:조사연구
• /
• 제11권1호
• /
• pp.1-18
• /
• 2010

본 논문에서는 패널조사에서 발생하는 웨이브 무응답을 대체하는 방법을 고찰하였다. 패널조사에서는 이전 조사 데이터를 무응답 대체에 활용할 수 있기 때문에 이러한 성질을 이용하면 횡단면 무응답 대체보다 더 효과적인 웨이브 무응답 대체법을 찾을 수 있다. 먼저 웨이브 무응답 대체를 사용하는 해외의 주요 패널조사를 살펴보고, 웨이브 무응답 대체방법 중 종단면 회귀대체법, 이월대체법, 최근방 회귀대체법, 그리고 행렬대체법을 고찰하였다. 그리고 웨이브 무응답 대체법의 성능을 비교하기 위하여 한국복지패널 데이터를 대상으로 모의실험을 실시하였다. 성능을 비교하기 위하여 평균대체, 회귀대체, 비대체, 최근방 대체, 핫덱 대체를 고려하였고 성능평가 지표로는 예측 정확성 지표와 추정 정확성 지표를 이용하였다. 모의실험 결과 비대체, 행렬대체는 두 지표 모두 우수했고, 회귀대체, 종단면 회귀대체, 이월대체는 예측 정확성은 우수한 반면 추정 정확성은 다소 떨어졌으며, 반대로 최근방 회귀대체, 최근방 대체, 핫덱 대체는 예측 정확성은 떨어지나 추정 정확성은 높은 것으로 나타났다. 마지막으로 평균 대체는 두 지표 모두 좋지 않았다.

• 응용통계연구
• /
• 제21권6호
• /
• pp.1109-1116
• /
• 2008

Biplots are the multivariate analogue of scatter plots. They are useful for giving a graphical description of the data matrix, for detecting patterns and for displaying results found by more formal methods of analysis. Nevertheless, when some values are missing in data matrix, most biplots are not directly applicable. In particular, we are interested in the shape variability of principal component biplot which is the most popular in biplots with missing values. For this, we estimate the missing data using the EM algorithm and mean imputation according to missing rates. Even though we estimate missing values of biplot of incomplete data, we have different shapes of biplots according to the imputation methods and missing rates. Therefore we propose a RMS(root mean square) for measuring and comparing the shape variability between the original biplots and the estimated biplots.