• Genomics & Informatics
• /
• 제20권3호
• /
• pp.34.1-34.11
• /
• 2022

Multilevel analysis is an appropriate and powerful tool for analyzing hierarchical structure data widely applied from public health to genomic data. In practice, however, we may lose the information on multiple nesting levels in the multilevel analysis since data may fail to capture all levels of hierarchy, or the top or intermediate levels of hierarchy are ignored in the analysis. In this study, we consider a multilevel linear mixed effect model (LMM) with single imputation that can involve all data hierarchy levels in the presence of missing top or intermediate-level clusters. We evaluate and compare the performance of a multilevel LMM with single imputation with other models ignoring the data hierarchy or missing intermediate-level clusters. To this end, we applied a multilevel LMM with single imputation and other models to hierarchically structured cohort data with some intermediate levels missing and to simulated data with various cluster sizes and missing rates of intermediate-level clusters. A thorough simulation study demonstrated that an LMM with single imputation estimates fixed coefficients and variance components of a multilevel model more accurately than other models ignoring data hierarchy or missing clusters in terms of mean squared error and coverage probability. In particular, when models ignoring data hierarchy or missing clusters were applied, the variance components of random effects were overestimated. We observed similar results from the analysis of hierarchically structured cohort data.

• 응용통계연구
• /
• 제19권1호
• /
• pp.57-67
• /
• 2006

표본조사에서 무응답은 여러 가지 이유로 발생하며, 이 때 응답자들의 정보로만 분석을 실시한다면 편향된 결과를 산출할 수 있어 보조변수를 이 용한 많은 무응답 대체 방법들이 연구되고 있다. 만일 결측자료 대체를 위한 보조변수들이 충분하지 않고 응답자들과 무응답자들 사이에 지역적 상관관계가 존재한다면 이를 결측자료 대체(missing data imputation)에 이용 할 수 있을 것이다. 본 논문에서는 2002년 강원지역의 농가경제 자료를 예제로 하여 공간상관을 이용한 무응답 대체 방법을 살펴보았으며, 공간상관이 존재할 경우 공간 대체 방법이 효율적임을 확인하였다.

• 응용통계연구
• /
• 제24권2호
• /
• pp.315-321
• /
• 2011

Gene expression microarray data often include multiple missing values. Most gene expression analysis (including gene clustering analysis); however, require a complete data matric as an input. In ordinary clustering methods, just a single missing value makes one abandon the whole data of a gene even if the rest of data for that gene was intact. The quality of analysis may decrease seriously as the missing rate is increased. In the opposite aspect, the imputation of missing value may result in an artifact that reduces the reliability of the analysis. To clarify this contradiction in microarray clustering analysis, this paper compared the accuracy of clustering with and without imputation over several microarray data having different missing rates. This paper also tested the clustering efficiency of several imputation methods including our propose algorithm. The results showed it is worthwhile to check the clustering result in this alternative way without any imputed data for the imperfect microarray data.

• 응용통계연구
• /
• 제29권3호
• /
• pp.539-547
• /
• 2016

임상시험에서 흔히 발생하는 결측치 중 이분형 결측치에 대한 논의를 하였다. 본 논문에서는 결측치가 발생하는 기재를 논의하고 기존의 여러 이분형 결측치 대체 방법과 수정된 결측치 대체방법을 소개하였다. 이후 각 결측치 대체 방법을 실제 자료에 적용하여 모의 실험을 진행하였다. 실제 자료의 성격 및 결측률의 변화에 따른 결측치 대체 방법들의 성능비교를 통해 진행하였다. 마지막으로 각 결측치 대체 방법에 대한 모의 실험 결과를 요약하고 토의하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.945-955
• /
• 2004

'Complete-case analysis' is easy to carry out and it may be fine with small amount of missing data. However, this method is not recommended in general because the estimates are usually biased and not efficient. There are numerous alternatives to complete-case analysis. One alternative is the single imputation. Some of the most common single imputation methods are reviewed and the performances are compared by simulation studies.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.585-598
• /
• 2007

It is so difficult to get complete data when we conduct a questionaire in actuality. And we get inefficient results if we analyze statistical tests with ignoring missing values. Therefore, we use imputation methods which evaluate quality of data. This study proposes a imputation method by decomposition and voting with ordinal data. First, data are sorted by each variable. After that, imputation methods are used by each decomposition level. And the last step is selection of values with voting. The proposed method is evaluated by accuracy and RMSE. In conclusion, missing values are related to each variable, median imputation method using decomposition and voting is powerful.

• 응용통계연구
• /
• 제30권3호
• /
• pp.463-473
• /
• 2017

임상시험에서 어떻게 결측치를 다룰 것인가 하는 것은 큰 문제이다. 주로 주분석에서 사용하는 ITT원칙은 결측치가 어떠한 메커니즘을 따른다는 가정 하에 결측치를 대체 하지만 가정에 대한 타당성이 불확실한 문제가 있다. 즉, 올바른 결측치 대체방법은 매우 중요하다. 본 연구에서는 Kang과 Kim (1997)이 제안한 일치도와 유지도의 개념을 이용하여 새로운 결측치 대체방법을 제안하였다. 또한 실제자료를 이용하여 예제를 제시하고 Monte Carlo 모의실험을 통하여 기존방법과 대체 성능을 비교하였다.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2003년도 Proceeding
• /
• pp.105-110
• /
• 2003

Collaborative filtering is one of the methodologies that are most widely used for recommendation system. It is based on a data matrix of each customer's preferences of products. There could be a lot of missing values in such preference. data matrix. This incomplete data is one of the reasons to deteriorate the accuracy of recommendation system. Multiple imputation method imputes m values for each missing value. It overcomes flaws of single imputation approaches through considering the uncertainty of missing values.. The objective of this paper is to suggest multiple imputation-based collaborative filtering approach for recommendation system to improve the accuracy in prediction performance. The experimental works show that the proposed approach provides better performance than the traditional Collaborative filtering approach, especially in case that there are a lot of missing values in dataset used for recommendation system.

• Quantitative Bio-Science
• /
• 제36권1호
• /
• pp.23-31
• /
• 2017

Datasets from DNA microarray experiments, which are in the form of large matrices of expression levels of genes, often have missing values. However, the existing statistical methods including the principle components analysis (PCA) and Hotelling's t-test are not directly applicable for the datasets having missing values due to the fact that they assume the observed dataset is complete in general. Many methods have been proposed in previous literature to impute the missing in the observed data. Troyanskaya et al. [1] study the k-nearest neighbor (kNN) imputation, Kim et al. [2] propose the local least squares (LLS) method and Rubin [3] propose the multiple imputation (MI) for missing values. To identify differentially expressed genes, we propose a new testing procedure when the missing exists in the observed data. The proposed procedure uses the Stouffer's z-scores and combines the test results of individual imputed samples, which are dependent to each other. We numerically show that the proposed test procedure based on MI performs better than the existing test procedures based on single imputation (SI) by comparing their ROC curves. We apply the proposed method to analyzing a public microarray data.

• 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.