• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.233-250
• /
• 2002

Cox's proportional hazard model is highly-used for the regression analysis of survival data in various fields. Regression diagnostics for the proportional hazards model, however, is not as well-known as the diagnostics for the classical linear models and so these diagnostic methods are not used widely in our practical data analyses. For this reason, we review the residuals proposed by several authors, and investigate how to use them in assessing the model. We also provide the results and interpretation with the analysis of PBC data using S-plus 2000 program.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.251-255
• /
• 2005

중도절단된 자료와 표본수가 적은 자료를 가지는 생존분석에서 생존율을 추정하거나 두 집단의 생존율을 비교할 때 정규분포 근사를 가정한 신뢰구간을 이용하는 데는 많은 어려움이 생긴다. 생존함수의 신뢰구간에 대한 중도절단을, 표본의 크기에 따른 다양한 상황의 모의실험을 통하여 Kaplan-Meier, Nelson, 적률 추정량 그리고 cox model의 ${\beta}$을 가지고 붓스트랩을 이용한 신뢰구간과 비모수 신뢰구간, 우도비 신뢰구간의 실제 포함 확률을 비교해보고자 한다.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.9
• /
• pp.4067-4070
• /
• 2014

Background: The Chinese Hui ethnic group has diverse origins, including Arab, Persian, Central Asian, and Mongol. The standardized mortality rate of gastric cancer in the Hui population is higher than the overall Chinese population. In this study, we investigated whether COX-2-765G>C polymorphism, an extensively studied polymorphism, contributes to gastric cancer and its precursor lesions (GPL) in the Chinese Hui ethnic group. Materials and Methods: COX-2-765G>C polymorphism was determined by pyrosequencing in 100 gastric cancer cases, 102 gastric cancerand its precursor lesions cases and 105 controls. Data were statistically analyzed using Chi-square tests and logistic regression models. Results: Among the Chinese Hui ethnic group COX-2-765 C allele carriers were at increased risk for gastric cancer (OR=1.977, 95%CI=1.104-3.541). We also found an interaction between COX-2 -765 C carriers and Helicobacter pylori infection and eating pickled vegetables. Conclusions: Our findings suggest a multi-step process of gene-environment interaction contributes to gastric carcinogenesis.

• Journal of the Korean Home Economics Association
• /
• v.42 no.1
• /
• pp.69-79
• /
• 2004

This study has examined factors of young married women's new entry in labor market after the birth of their first child. For the dynamic analysis, the Cox Regression Hazard Model is applied. The following results are obtained： First, about 33％ of married women who did not have a job at the pre-birth enter in labor market at the post-birth. Second, compared to those out of the labor force, women who succeeded in finding their first jobs after the birth of their first child are more likely to be younger, have baby-sitters, have working experiences in the past, and have lower level of household income. Third, age, having baby-sitter and the experience of job transition are vital factors in entering the labor market after the first child birth.

• Communications for Statistical Applications and Methods
• /
• v.24 no.2
• /
• pp.115-127
• /
• 2017

This paper proposes a Bayesian test for the equivalence of survival functions in multiple groups. Proposed Bayesian test use the model of Cox's regression with time-varying coefficients. B-spline expansions are used for the time-varying coefficients, and the proposed test use only the partial likelihood, which provides easier computations. Various simulations of the proposed test and typical tests such as log-rank and Fleming and Harrington tests were conducted. This result shows that the proposed test is consistent as data size increase. Specifically, the power of the proposed test is high despite the existence of crossing hazards. The proposed test is based on a Bayesian approach, which is more flexible when used in multiple tests. The proposed test can therefore perform various tests simultaneously. Real data analysis of Larynx Cancer Data was conducted to assess applicability.

• Communications for Statistical Applications and Methods
• /
• v.23 no.3
• /
• pp.189-201
• /
• 2016

In survival analysis, the Nelson-Aalen estimator and Peterson estimator are often used to estimate a cumulative hazard function in randomly right censored data. In this paper, we suggested the smoothing version of the cumulative hazard function estimators using a Bezier curve. We compare them with the existing estimators including a kernel smooth version of the Nelson-Aalen estimator and the Peterson estimator in the sense of mean integrated square error to show through numerical studies that the proposed estimators are better than existing ones. Further, we applied our method to the Cox regression where covariates are used as predictors and suggested a survival function estimation at a given covariate.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.921-932
• /
• 2015

This study analyzed military personnel survivability in regards to offensive operations according to the scientific military training data of a reinforced infantry battalion. Scientific battle training was conducted at the Korea Combat Training Center (KCTC) training facility and utilized scientific military training equipment that included MILES and the main exercise control system. The training audience freely engaged an OPFOR who is an expert at tactics and weapon systems. It provides a statistical analysis of data in regards to state-of-the-art military training because the scientific battle training system saves and utilizes all training zone data for analysis and after action review as well as offers training control during the training period. The methodologies used the Cox PH modeling (which does not require parametric distribution assumptions) and decision tree modeling for survival data such as CART, GUIDE, and CTREE for richer and easier interpretation. The variables that violate the PH assumption were stratified and analyzed. Since the Cox PH model result was not easy to interpret the period of service, additional interpretation was attempted through univariate local regression. CART, GUIDE, and CTREE formed different tree models which allow for various interpretations.

• Journal of Periodontal and Implant Science
• /
• v.42 no.5
• /
• pp.151-157
• /
• 2012

Purpose: Cyclooxygenase (COX) enzyme catalyzes the production of prostaglandins, which are important mediators of tissue destruction in periodontitis. Single nucleotide polymorphisms of $COX_2$ enzyme have been associated with increasing susceptibility to inflammatory diseases. The present study evaluates the association of two single nucleotide polymorphisms in $COX_2$ gene (-1195G>A and $8_{473}$C>T) with chronic periodontitis in North Indians. Methods: Both SNPs and their haplotypes were used to explore the associations between $COX_2$ polymorphisms and chronic periodontitis in 56 patients and 60 controls. Genotyping was done by polymerase chain reaction followed by restriction fragment length polymorphism. Chi-square test and logistic regression analysis were performed for association analysis. Results: By the individual genotype analysis, mutant genotypes (GA and AA) of $COX_2$-1195 showed more than a two fold risk (odds ratio [OR]>2) and $COX_2$ $8_{473}$ (TC and CC) showed a reduced risk for the disease, but the findings were not statistically significant. Haplotype analysis showed that the frequency of the haplotype AT was higher in the case group and a significant association was found for haplotype AT (OR, 1.79; 95% confidence interval, 1.03 to 3.11; P=0.0370) indicating an association between the AT haplotype of $COX_2$ gene SNPs and chronic periodontitis. Conclusions: Individual genotypes of both the SNPs were not associated while haplotype AT was found to be associated with chronic periodontitis in North Indians.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.8
• /
• pp.4101-4105
• /
• 2016

Background: Mortality among Iranian patients with colorectal cancer has not been fully examined and the factors associated with their survival are still controversial. This study aimed to determine the mortality rate and its related factors among the patients with colorectal cancer in southwestern regions in Iran. Materials and Methods: This prospective cohort study was conducted on 220 patients with colorectal cancer referred to Fahighi Hospital, Shiraz, Iran from 2009 to 2014. Data were collected from the patients' medical records and were analyzed using Cox regression analysis. Results: Over a median follow-up of 29.3 months, 56 out of the 220 patients (25.5%) died, 32 (14.5%) aged below 40 years, and 45.5% were female. Based on the results of multiple Cox regression analysis, family history of gastrointestinal cancer, stage III, former smoking, type of lesion (fungative and polypoid), and opium use were associated with a greater risk of colorectal cancer mortality (all P<0.05). Conclusions: This cohort study found that the mortality rate of colorectal cancer in Iran is lower than that in European countries. In addition, behavioral and clinical factors were significantly associated with the survival rate. Addressing the related factors would help healthcare providers and physicians provide the best care and improve the survival rate.

• Korean Journal of Social Welfare
• /
• v.39
• /
• pp.210-237
• /
• 1999

The primary purpose of this study is to empirically examine the determinants of reemployment of the unemployed after the crash of Korea's economy in 1997. This study also investigates the effects of the government unemployment programs on reemployment of the program beneficiaries. Using the data from the 1998 Survey on Unemployment Condition and Welfare Needs, co-directed by the Korea Institute of Health and Welfare and the Korea Institute of Labor Policy, a Cox regression analysis was conducted. The study results suggested that, in general, the government unemployment programs did not have noticeable effects on reemployment of the beneficiaries. The study, however, found that the effect of the government programs varied, depending on the mode of unemployment-exit, that is, full-time versus part-time reemployment. In addition, the effects of such factors on reemployment as socio-economic characteristics of the unemployed, characteristics of households with unemployed family members, and previous job characteristics are also examined. Based on the study findings, some policy implications are discussed, and suggestions are made for improving the current unemployment programs.