• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2004년도 학술발표논문집
• /
• pp.237-241
• /
• 2004

In standard time-to-event or survival analysis, the occurrence times of the event of interest are observed exactly or are right-censored. However in certain situations such as the AIDS data, the incubation period which is the time between HIV infection time and the diagnosis of AIDS is usually doubly censored. That is the HIV infection time Is interval censored and also the time of the diagnosis of AIDS is right censored. In this paper, we Impute the Interval censored infection time using the conditional mean imputation and estimate the coefficient factor of the regression analysis for the incubation period using Gibbs sampler. We applied parametric and semi-parametric methods for the analysis of the Incubation period and compared the results.

• Communications for Statistical Applications and Methods
• /
• 제8권3호
• /
• pp.815-822
• /
• 2001

The aim of this study is to estimate the seroconversion date of the human immunodeficiency virus(HIV) infection for the HIV infected patients in Korea. Data are collected from two cohorts. The first cohort is a group of "seroprevalent" patients who were seropositive and AIDS-free at entry. The other is a group of "seroincident" patients who were initially seronegative but later converted to HIV antibody-positive. The seroconversion dates of the seroincident cohort are available while those of the seroprevalent cohort are not. Estimation of seroconversion date is important because it can be used to calculate the incubation period of AIDS which is defined as the elapsed time between the HIV infection and the development of AIDS. In this paper, a Weibull regression model Is fitted for the seroincident cohort using information about the elapsed time since seroconversion and the CD4$^{+}$ cell count.The seroconversion dates for the seroprevalent cohort are imputed on the basis of the marker of maturity of HIV infection percent of CD4$^{+}$cell count.unt.

• 응용통계연구
• /
• 제24권5호
• /
• pp.871-881
• /
• 2011

In this paper we propose a logistic regression method to estimate the survival function and the median survival time in interval-censored data. The proposed method is motivated by the data augmentation technique with no sacrifice in augmenting data. In addition, we develop a cross validation criterion to determine the size of data augmentation. We compare the proposed estimator with other existing methods such as the parametric method, the single point imputation method, and the nonparametric maximum likelihood estimator through extensive numerical studies to show that the proposed estimator performs better than others in the sense of the mean squared error. An illustrative example based on a real data set is given.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.287-296
• /
• 2022

Today, air pollution is becoming a severe issue worldwide and various policies are being implemented to solve environmental pollution. In major cities, public bicycles are installed and operated to reduce pollution and solve transportation problems, and operational information is collected in real time. However, research using public bicycle operation information data has not been processed. This study uses the daily weather data of Korea Meteorological Agency and real-time air pollution data of Korea Environment Corporation to predict the amount of daily rental bicycles. Cross- validation, principal component analysis and multiple regression analysis were used to determine the independent variables of the predictive model. Then, the study selected the elements that satisfy the significance level, constructed a model, predicted the amount of daily rental bicycles, and measured the accuracy.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권10호
• /
• pp.4567-4575
• /
• 2016

A number of studies have evidenced the effect of modifiable lifestyle factors such as diet, breastfeeding and nutritional status on breast cancer risk. However, none have addressed the missing data problem in nutritional epidemiologic research in South America. Missing data is a frequent problem in breast cancer studies and epidemiological settings in general. Estimates of effect obtained from these studies may be biased, if no appropriate method for handling missing data is applied. We performed Multiple Imputation for missing values on covariates in a breast cancer case-control study of $C{\acute{o}}rdoba$ (Argentina) to optimize risk estimates. Data was obtained from a breast cancer case control study from 2008 to 2015 (318 cases, 526 controls). Complete case analysis and multiple imputation using chained equations were the methods applied to estimate the effects of a Traditional dietary pattern and other recognized factors associated with breast cancer. Physical activity and socioeconomic status were imputed. Logistic regression models were performed. When complete case analysis was performed only 31% of women were considered. Although a positive association of Traditional dietary pattern and breast cancer was observed from both approaches (complete case analysis OR=1.3, 95%CI=1.0-1.7; multiple imputation OR=1.4, 95%CI=1.2-1.7), effects of other covariates, like BMI and breastfeeding, were only identified when multiple imputation was considered. A Traditional dietary pattern, BMI and breastfeeding are associated with the occurrence of breast cancer in this Argentinean population when multiple imputation is appropriately performed. Multiple Imputation is suggested in Latin America's epidemiologic studies to optimize effect estimates in the future.

• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.367-376
• /
• 2011

BLS 가중치보정법은 사업체 조사 시 발생한 무응답 및 이상점을 처리하기 위해 사용하는 가중치 보정방법중의 하나이다. 최근의 연구에 의하면 총계 추정에 있어 BLS 무응답 가중치보정법의 결과가 비추정법을 사용한 대체 결과와 일치하는 것으로 알려졌다. 본 논문에서는 이상점과 무응답이 동시에 있는 경우, BLS 무응답 가중치보정법을 비추정 대체법으로 바꾸어 총계를 추정하는 새로운 방법을 제안하였다. 매월 노동 통계 자료를 이용한 모의 실험을 통하여 제안된 방법의 우수성을 확인하였다.

• 응용통계연구
• /
• 제15권1호
• /
• pp.33-43
• /
• 2002

범주형 데이터의 결측치 추정을 위하여 최빈 범주법, 로지스틱 회귀분석, 연관규칙과 같은 다양한 방법이 연구되어 왔다. 본 연구에서는 이러한 방법의 추정 값을 결합하는 신경망 융합과 투표융합 방법을 제안하고 이의 성능을 시뮬레이션을 이용하여 비교하였다. 실험에 사용된 데이터의 특성을 나타내는 인자로는 (1) 입출력 변수간의 연결함수, (2) 데이터의 크기, (3) 노이즈의 크기 (4) 결측치의 비율, (5) 결측발생 함수를 사용하였다. 분석결과는 다음과 같다. 데이터의 크기가 작고 결측 발생 비율이 높으면 최빈 범주법, 연관규칙, 신경망 융합의 성능이 높게 나타났으며 데이터의 크기가 작고 결측발생 확률이 결측이 안된 나머지 변수에 높은 의존관계가 있으면 로지스틱 회귀분석, 신경망 융합의 성능이 높게 나타났다. 데이터의 크기가 크고, 결측치의 비율이 낮으면서, 노이즈가 크고 결측발생 확률이 결측이 안된 나머지 변수에 높은 의존관계가 있으면 신경망 융합의 성능이 높게 나타났다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권1호
• /
• pp.217-223
• /
• 2016

Outcome misclassification is widespread in classification problems, but methods to account for it are rarely used. In this paper, the problem of inference with misclassified multinomial logit data with a large number of multinomial parameters is addressed. We have had a significant swell of interest in the development of novel methods to infer misclassified data. One simulation study is shown regarding how seriously misclassification issue occurs if the number of categories increase. Then, using the group lasso regression, we will show how the best model should be fitted for that kind of multinomial regression problems comprehensively.

• Communications for Statistical Applications and Methods
• /
• 제9권2호
• /
• pp.565-576
• /
• 2002

We propose a new sampling design for the 2001 Health Index Survey at Seoul. In this stratified two-stage sampling design, the ED(enumeration district) of 2000 Population and Housing Census is used as primary sampling unit and the Gu is used as stratification variable in order to obtain the sub-domain estimate for 25 Gu's as well as population estimate for Seoul. The sample ED's are systematically selected after the Ed's are ordered by location and property to obtain a representative sample. And also, the imputation methods for item nonresponses are suggested.

• 대한교통학회지
• /
• 제28권3호
• /
• pp.61-74
• /
• 2010

지능형 교통체계는 실시간 교통자료를 수집하고 방대한 양의 이력자료를 축적한다. 그러나 방대한 이력자료는 효율적으로 관리/이용되지 않고 있는 실정이다. ADMS와 같은 자료관리시스템이 도입되면서, 이력자료의 잠재적 활용성은 급격히 증대되고 있다. 그러나 자료관리스템의 교통자료는 다량의 누락자료를 포함하고 있다. 누락자료는 장기간에 걸쳐 빈번하게 교통자료를 이용할 수 없게 하기 때문에, 이력자료를 활용하는데 있어 주된 장애요인 중 하나이다. 따라서 누락자료 추정기법은 자료관리시스템에서 주요한 역할을 수행하게 된다. 이러한 한계를 극복하기 위하여, 본 연구에서는 자료관리스템에 탑재가 용이하며 이력자료에 포함된 누락자료를 추정하기 위한 누락자료 추정모형을 개발하였다. 개발모형은 비모수회귀식(NPR)을 기반으로 개발되었으며, 이력자료의 다양한 교통자료 패턴을 이용하고 현실적인 요구사항(변수 최소화, 연산속도, 다양한 형태의 누락자료 보정, 다중대체)을 충족하도록 설계되었다. 모형의 평가는 다양한 누락자료 형태의 상태에서 수행되었으며, 자료관리시스템에 탑재되기 위해 요구되는 정확도, 연산 수행속도에서 기존에 보고된 모형보다 우수한 성능을 보였다.