• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.583-604
• /
• 2017

The most popular regression model for the analysis of time-to-event data is the Cox proportional hazards model. While the model specifies a parametric relationship between the hazard function and the predictor variables, there is no specification regarding the form of the baseline hazard function. A critical assumption of the Cox model, however, is the proportional hazards assumption: when the predictor variables do not vary over time, the hazard ratio comparing any two observations is constant with respect to time. Therefore, to perform credible estimation and inference, one must first assess whether the proportional hazards assumption is reasonable. As with other regression techniques, it is also essential to examine whether appropriate functional forms of the predictor variables have been used, and whether there are any outlying or influential observations. This article reviews diagnostic methods for assessing goodness-of-fit for the Cox proportional hazards model. We illustrate these methods with a case-study using available R functions, and provide complete R code for a simulated example as a supplement.

• 응용통계연구
• /
• 제30권3호
• /
• pp.427-439
• /
• 2017

공변량(covariate)이 존재하는 경우, 각 처리군 간 효과의 차이를 검정하기 위한 대표적인 비모수적 방법에는 Quade (1967)가 제안한 검정법이 있다. 또한 반응변수에 대해 공변량으로 단순선형회귀분석을 실시하여 얻은 잔차에 대해 일원배치분산분석과 Kruskal Wallis가 제안한 방법을 적용하는 방법, 그리고 Hwang과 Kim (2012)이 제안한 비모수적 도구인 위치(placement)를 이용한 방법이 있다. 본 논문에서는 공분산분석 모형에서 Hwang과 Kim (2012)이 제안한 방법을 확장하여 공분산분석에서의 새로운 방법을 제안하였다. 또한 모의실험(Monte Carlo simulation study)을 통하여 기존의 검정법들과 제안한 방법의 검정력을 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.187-199
• /
• 2003

We deal with the problem of testing a sequence of independent normal random variables with constant, known or unknown, variance for no change in mean versus alternatives with a single change-point. Various tests based on the likelihood ratio and recursive residuals, score statistics and cusums are studied. Proposed tests are modified version of Buckley's cusum statistics. A comparison study of various change-point test statistics is done by Monte Carlo simulation with S-plus software.

• Nutrition Research and Practice
• /
• 제9권4호
• /
• pp.404-410
• /
• 2015

BACKGROUND/OBJECTIVES: Although the association of body mass index (BMI) with metabolic syndrome (MetS) is well documented, there is little knowledge on the independent and joint associations of BMI and physical activity with MetS risk based on a continuous scoring system. This study was designed to explore the effect of physical activity on interactions between excess body weight and continuous metabolic syndrome (cMetS) in a nationwide survey of Iranian children and adolescents. SUBJECTS/METHODS: Data on 5,625 school students between 10 and 18 years of age were analyzed. BMI percentiles, screen time activity (STA), leisure time physical activity (LTPA) levels, and components of cMetS risk score were extracted. Standardized residuals (z-scores) were calculated for MetS components. Linear regression models were used to study the interactions between different combinations of cMetS, LTPA, and BMI percentiles. RESULTS: Overall, 984 (17.5%) subjects were underweight, whereas 501 (8.9%) and 451 (8%) participants were overweight and obese, respectively. All standardized values for cMetS components, except fasting blood glucose level, were directly correlated with BMI percentiles in all models (P-trend < 0.001); these associations were independent of STA and LTPA levels. Linear associations were also observed among LTPA and standardized residuals for blood pressure, high-density lipoprotein, and waist circumference (P-trend < 0.01). CONCLUSIONS: Our findings suggest that BMI percentiles are associated with cMetS risk score independent of LTPA and STA levels.

• 대한방사선기술학회지:방사선기술과학
• /
• 제22권2호
• /
• pp.41-46
• /
• 1999

Osteoporosis, which causes mainly fracture of the spine, proximal femur and distal radius by minimal trauma, is a major public health problem and its prevalence is steadily increasing in Korea according to the development of public health care. There are reliable methods for diagnosis based on bone densitometry. Early detection and intervention are important for reducing the incidence of fractures. A consensus definition of osteoporosis, based on bone density measurement, has been developed by the World Health Organization(WHO). In this study, bone mineral density(RMD) was measured by dual energy x-ray absorptiometry(DEXA) at the proximal femur and lumbar spine in 132 post-menopausal women. The purpose of this study is to find influential factors on the BMD of the proximal femur and the lumbar spine and to analyze correlation between BMD and the problematic factors. We obtained the following results : 1. Mean BMD score, T-score and Z-score of the proximal femur were $0.81(g/cm^2)$, -2.45(S.D.) and -2.09(S.D.) respectively and in the lumbar spine were $0.83(g/cm^2)$, -2.02(S.D.), -2.43(S.D.) respectively. 2. In correlation analysis between BMD and many factors, correlation coefficients were -0.467, 0.212, -0.321 and 0.241 in age, height, duration after menopause respectively. BMI and the residuals were comparatively small. 3. Correlation coefficients to age matched BMD, in height and body weight were 0.222 and 0.241, in age and duration after menopause were -0.268, -0.282. 4. The fracture threshold of proximal femur BMD to the 90th percentile was $0.845(g/cm^2)$. 5. At the result of multiple regression analysis, age, body weight, $BMI(kg/m^2)$ and duration after menopause described as significant variables.

• 한국항해항만학회지
• /
• 제39권6호
• /
• pp.507-514
• /
• 2015

본 연구는 항만 물류배후단지에 입주하여 운영하는 입주업체들의 효율성을 분석하는 것을 연구의 목적으로 하였다. 인천항과 부산신항 항만 물류배후단지 13개 입주기업을 효율성 분석대상으로 하였으며, 투입변수는 투자액, 면적, 종업원 수를 사용하였고, 산출변수는 물동량과 매출액을 선정하였다. 효율성 분석방법으로는 전통적인 CCR 모형과 BCC 모형을 적용하고 이들의 한계점을 극복하기 위해 초효율성 모형과 Super-SBM 모형을 적용하였다. 초효율성 모형의 분석결과, 평균값은 0.777, 표준편차는 0.541로 나타나 각 기업 간 효율성 점수 차이는 33% 정도 존재하는 것으로 분석되었다. Super-SBM 모형의 분석결과, 평균값은 0.649, 표준편차는 0.489로 초효율성 모형에서 여분을 고려할 경우 기업 간 효율성 점수 평균이 약 13% 정도 감소한 것으로 나타났다. 이러한 감소의 의미는 비방사형 여분이 존재하는 DMU의 효율성 점수하락이 평균 13% 정도 됨을 의미한다. 투입요소의 비효율성 분석결과 면적 -33%, 투자액 -33%에 비해 종업원 수의 비효율성이 -45%로 가장 큰 것으로 분석되었다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제19권10호
• /
• pp.1399-1403
• /
• 2006

A total of 80 cows, including 40 top mastitis resistant and 40 top mastitis susceptible animals as Group I and Group II, were selected from a population of 520 cows based on clinical mastitis occurrence. PCR-SSCP analysis on four fragments within the 5'region and two fragments of Exons 4,15 of bovine lactoferrin (bLF) revealed that four fragments-P1,P4,E4,E15-had polymorphisms which totally included six base mutations, and only two of them had significant differences in allele frequencies between resistant and susceptible groups, P1 (53.7% vs. 70.0%, p<0.05) and P4 (55.0% vs. 68.8%, p<0.05). Further study on these two promising markers combined with the milk performance traits of cows demonstrated that their selection would result in higher fat percentage (p<0.05), lower Somatic Cell Score (SCS) (p<0.05) and Clinical Mastitis Residuals (CMR) (p<0.01) indicating higher mastitis resistance and lower milk yield (p<0.05). The putative transcription factor binding sites in the 5'region were also studied by using MatInspector 7.2.2 software, and two signal pathways regulating the expression of bLF including the NF-${\kappa}B$ pathway and nuclear hormone receptor pathway were predicted.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권11호
• /
• pp.1537-1544
• /
• 2015

Meat and carcass quality attributes are of crucial importance influencing consumer preference and profitability in the pork industry. A set of 400 Berkshire pigs were collected from Dasan breeding farm, Namwon, Chonbuk province, Korea that were born between 2012 and 2013. To perform genome wide association studies (GWAS), eleven meat and carcass quality traits were considered, including carcass weight, backfat thickness, pH value after 24 hours (pH24), Commission Internationale de l'Eclairage lightness in meat color (CIE L), redness in meat color (CIE a), yellowness in meat color (CIE b), filtering, drip loss, heat loss, shear force and marbling score. All of the 400 animals were genotyped with the Porcine 62K SNP BeadChips (Illumina Inc., USA). A SAS general linear model procedure (SAS version 9.2) was used to pre-adjust the animal phenotypes before GWAS with sire and sex effects as fixed effects and slaughter age as a covariate. After fitting the fixed and covariate factors in the model, the residuals of the phenotype regressed on additive effects of each single nucleotide polymorphism (SNP) under a linear regression model (PLINK version 1.07). The significant SNPs after permutation testing at a chromosome-wise level were subjected to stepwise regression analysis to determine the best set of SNP markers. A total of 55 significant (p<0.05) SNPs or quantitative trait loci (QTL) were detected on various chromosomes. The QTLs explained from 5.06% to 8.28% of the total phenotypic variation of the traits. Some QTLs with pleiotropic effect were also identified. A pair of significant QTL for pH24 was also found to affect both CIE L and drip loss percentage. The significant QTL after characterization of the functional candidate genes on the QTL or around the QTL region may be effectively and efficiently used in marker assisted selection to achieve enhanced genetic improvement of the trait considered.

• 농업생명과학연구
• /
• 제46권1호
• /
• pp.123-131
• /
• 2012

본 연구는 한우 성장형질간의 상관분석을 통하여 6, 12, 18, 24개월 체중, 일당증체량, 도체형질과 18개월 체형형질간의 성장단계별 형질간의 상관관계를 파악하고자 실시하였다. 분석에 이용한 자료는 농협중앙회 한우개량사업소에서 후대 검정을 실시한 2004년에서 2008년까지의 거세우 1,838두의 체중과 체형형질을 이용하였고 도체형질은 24개월령 도축성적을 이용하였다. 본 논문에서 상관분석은 관측치 상관과 고정효과를 고려한 잔차상관으로 하였다. 도축 전 생체중과 도체중은 0.92의 높은 상관관계를 가지고 있었다. 도체형질에서는 육량지수와 등지방두께 간에 -0.92의 높은 부의 상관을 보였다. 체형형질에서 십자부고와 체고는 0.89로서 높은 상관관계가 있었으며 흉폭과 흉심이 0.73의 상관관계를 나타냈다. 체위 형질간 상관에서 요각폭에 대해 흉심과 흉폭이 각각 0.75, 0.74의 상관을 보였고 곤폭은 요각폭과 0.74의 상관을 보였다. 좌골폭에 대해서는 흉심, 흉폭, 요각폭, 곤폭이 각각 0.73, 0.70, 0.75, 0.75로 정의 높은 상관을 나타냈다. 체장과 도체중간의 관측치상관은 0.48이였고, 흉위는 도체중과 잔차상관이 0.51로 다른 도체형질보다 상관정도가 높게 나타났다. 따라서 본 연구결과는 한우 후대검정우 유전평가시 기초 자료로 활용 가능할 것으로 예상된다.