• Journal of the Korean Data and Information Science Society
• /
• v.23 no.6
• /
• pp.1045-1054
• /
• 2012

Support vector machine is known to be the very useful statistical method in classification and nonlinear function estimation. In this paper we propose a monotone support vector regression (SVR) for the estimation of monotonically decreasing function. The proposed monotone SVR is applied to smooth the Kaplan-Meier estimate of survival function. Experimental results are then presented which indicate the performance of the proposed monotone SVR using survival functions obtained by exponential distribution.

• Communications for Statistical Applications and Methods
• /
• v.12 no.3
• /
• pp.807-818
• /
• 2005

In this paper we propose an estimation method for regression quantiles with left-truncated and right-censored data. The estimation procedure is based on the weight determined by the Kaplan-Meier estimate of the distribution of the response. We show how the proposed regression quantile estimators perform through analyses of Stanford heart transplant data and AIDS incubation data. We also investigate the effect of censoring on regression quantiles through simulation study.

• Journal of the Korean Statistical Society
• /
• v.32 no.1
• /
• pp.25-32
• /
• 2003

In this paper, we define the mean life process for the right censored data and show the asymptotic equivalence between two kinds of the mean life processes. We use the Kaplan-Meier and Susarla-Van Ryzin estimates as the estimates of survival function for the construction of the mean life processes. Also we show the asymptotic equivalence between two mean residual life processes as an application and finally discuss some difficulties caused by the censoring mechanism.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.957-968
• /
• 2021

Inverse censoring probability weighting (ICPW) is a popular technique in survival data analysis. In applications of the ICPW technique such as the censored regression, it is crucial to accurately estimate the censoring probability. A simulation study is undertaken in this article to see how censoring probability estimate influences model performance in censored regression using the ICPW scheme. We compare three censoring probability estimators, including Kaplan-Meier (KM) estimator, Cox proportional hazard model estimator, and local KM estimator. For the local KM estimator, we propose to reduce the predictor dimension to avoid the curse of dimensionality and consider two popular dimension reduction tools: principal component analysis and sliced inverse regression. Finally, we found that the Cox proportional hazard model estimator shows the best performance as a censoring probability estimator in both mean and median censored regressions.

• The Korean Journal of Applied Statistics
• /
• v.25 no.2
• /
• pp.311-319
• /
• 2012

The simplest and the most important distribution in survival analysis is exponential distribution. Koziol and Green (1976) derived Cram$\acute{e}$r-von Mises statistic's randomly censored version based on the Kaplan-Meier product limit estimate of the distribution function; however, it could not be practical for a real data set since the statistic is for testing a simple goodness of fit hypothesis. We generalized it to the composite hypothesis for exponentiality with an unknown scale parameter. We also considered the classical Kolmogorov-Smirnov statistic and generalized it by the exact same way. The two statistics are compared through a simulation study. As a result, we can see that the generalized Koziol-Green statistic has better power in most of the alternative distributions considered.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.883-891
• /
• 2011

For survival data we sometimes want to test a log normality hypothesis that can be changed into normality by transforming the survival data. Hence the Shapiro-Wilk type statistic for normality is generalized to randomly censored data based on the Kaplan-Meier product limit estimate of the distribution function. Koziol and Green (1976) derived Cram$\acute{e}$r-von Mises statistic's randomly censored version under the simpl hypothesis. These two test statistics are compared through a simulation study. As for the distribution of censoring variables, we consider Koziol and Green (1976)'s model and other similar models. Through the simulation results, we can see that the power of the proposed statistic is higher than that of Koziol-Green statistic and that the proportion of the censored observations (rather than the distribution of censoring variables) has a strong influence on the power of the proposed statistic.

• The Mathematical Education
• /
• v.31 no.2
• /
• pp.133-140
• /
• 1992

The problem of estimating a smooth distribution function F at a point $\tau$ based on randomly right censored data is treated under certain smoothness conditions on F . The asymptotic performance of a certain class of kernel estimators is compared to that of the Kap lan-Meier estimator of F($\tau$). It is shown that the .elative deficiency of the Kaplan-Meier estimate. of F($\tau$) with respect to the appropriately chosen kernel type estimate. tends to infinity as the sample size n increases to infinity. Strong uniform consistency and the weak convergence of the normalized process are also proved.

• Knowledge Management Research
• /
• v.11 no.2
• /
• pp.95-109
• /
• 2010

The objectives of this study are to identify the survival function (hazard function) of small and medium enterprises by using technology rating data for the companies guaranteed by Korea Technology Finance Corporation (KOTEC), and to figure out the factors that affects their survival. To serve the purposes, this study uses Kaplan-Meier Analysis as a non-parametric method and Cox proportional hazards model as a semi-parametric one. The 17,396 guaranteed companies that assessed from July 1st in 2005 to December 31st in 2009 are selected as samples (16,504 censored data and 829 accident data). The survival time is computed with random censoring (Type III) from July in 2005 as a starting point. The results of the analysis show that Kaplan-Meier Analysis and Cox proportional hazards model are able to readily estimate survival and hazard function and to perform comparative study among group variables such as industry and technology rating level. In particular, Cox proportional hazards model is recognized that it is useful to understand which technology rating items are meaningful to company's survival and how much they affect it. It is considered that these results will provide valuable knowledge for practitioners to find and manage the significant items for survival of the guaranteed companies through future technology rating.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.115-121
• /
• 2017

This paper is to introduce the main modeling assumptions and data structures associated with right-censored data to describe the successful methodological ideas for analyzing such a field-failure-data when components operating in different environments. The Kaplan - Meier method is the most popular method used for survival analysis. Together with the log-rank test, it may provide us with an opportunity to estimate survival probabilities and to compare survival between groups. An important advantage of the Kaplan - Meier curve is that the method can take into account some types of censored data, particularly right-censoring. The above non-parametric method was used to verify the equality of parts life used in different environments. After that, we performed the life distribution analysis using the parametric method. We simulated data from three distributions: exponential, normal, and Weibull. This allowed us to compare the results of the estimates to the known true values and to quantify the reliability indices. Here we used the Akaike information criterion to find a suitable life time distribution. If the Akaike information criterion is the smallest, the best model of failure data is presented. In this paper, no-nparametrics and parametrics methods are analyzed using R program which is a popular statistical program.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.21
• /
• pp.9453-9458
• /
• 2014

Background: Breast cancer is the second leading cause of cancer death for women in the United States. Differences in survival of breast cancer have been noted among racial and ethnic groups, but the reasons for these disparities remain unclear. This study presents the characteristics and the survival curve of two racial and ethnic groups and evaluates the effects of race on survival times by measuring the lifetime data-based half-normal model. Materials and Methods: The distributions among racial and ethnic groups are compared using female breast cancer patients from nine states in the country all taken from the National Cancer Institute's Surveillance, Epidemiology, and End Results cancer registry. The main end points observed are: age at diagnosis, survival time in months, and marital status. The right skewed half-normal statistical probability model is used to show the differences in the survival times between black Hispanic (BH) and black non-Hispanic (BNH) female breast cancer patients. The Kaplan-Meier and Cox proportional hazard ratio are used to estimate and compare the relative risk of death in two minority groups, BH and BNH. Results: A probability random sample method was used to select representative samples from BNH and BH female breast cancer patients, who were diagnosed during the years of 1973-2009 in the United States. The sample contained 1,000 BNH and 298 BH female breast cancer patients. The median age at diagnosis was 57.75 years among BNH and 54.11 years among BH. The results of the half-normal model showed that the survival times formed positive skewed models with higher variability in BNH compared with BH. The Kaplan-Meir estimate was used to plot the survival curves for cancer patients; this test was positively skewed. The Kaplan-Meier and Cox proportional hazard ratio for survival analysis showed that BNH had a significantly longer survival time as compared to BH which is consistent with the results of the half-normal model. Conclusions: The findings with the proposed model strategy will assist in the healthcare field to measure future outcomes for BH and BNH, given their past history and conditions. These findings may provide an enhanced and improved outlook for the diagnosis and treatment of breast cancer patients in the United States.