• Communications for Statistical Applications and Methods
• /
• 제23권4호
• /
• pp.287-296
• /
• 2016

Subjects on one side of the covariate population can be allocated to the inferior treatment when there is interaction between the covariate and treatment along with a response-adaptive (RA) design without covariate adjustment. An RA design allows a newly entered subject to have a better chance so that the subject is treated by a superior treatment based on cumulative information from previous subjects. A covariate-adjusted response-adaptive (CARA) is the same as RA design and additionally adjusts the allocation based on individual covariate information. A comparison has been made for the sequential estimation procedure with and without covariate adjustment to see how ignoring significantly interactive covariate affects the correct treatment allocation. Using logistic models, we present simulation results regarding the coverage probability of treatment effect, correct allocation, and stopping time.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.217-227
• /
• 2015

In observational study, handling confounders is a primary issue in measuring treatment effect of interest. Historically, a regression with covariate adjustment (covariate-adjusted regression) has been the typical approach to estimate treatment effect incorporating potential confounders into model. However, ever since the introduction of the propensity score, covariate-adjusted regression has been gradually replaced in medical literatures with various balancing methods based on propensity score. On the other hand, there is only a paucity of researches assessing propensity score methods compared with the covariate-adjusted regression. This paper examined the performance of propensity score methods in estimating risk difference and compare their performance with the covariate-adjusted regression by a Monte Carlo study. The study demonstrated in general the covariate-adjusted regression with variable selection procedure outperformed propensity-score-based methods in terms both of bias and MSE, suggesting that the classical regression method needs to be considered, rather than the propensity score methods, if a performance is a primary concern.

• Communications for Statistical Applications and Methods
• /
• 제21권5호
• /
• pp.387-393
• /
• 2014

Recurrent gap times are analyzed with diverse methods under several assumptions such as a marginal model or a frailty model. Several resampling techniques have been recently suggested to estimate the covariate effect; however, these approaches can be applied with a time-fixed covariate. According to simulation results, these methods result in biased estimates for a time-varying covariate which is often observed in a longitudinal study. In this paper, we extend a resampling method by incorporating new weights and sampling scheme. Simulation studies are performed to compare the suggested method with previous resampling methods. The proposed method is applied to estimate the effect of an educational program on traffic conviction data where a program participation occurs in the middle of the study.

• Communications for Statistical Applications and Methods
• /
• 제23권4호
• /
• pp.335-341
• /
• 2016

Interval censored failure time data often occurs in an observational study where a subject is followed periodically. Instead of observing an exact failure time, two inspection times that include it are made available. Several methods have been suggested to analyze interval censored failure time data (Sun, 2006). In this article, we are concerned with a binary time-varying covariate whose changing time is interval censored. A modified estimating equation is proposed by extending the approach suggested in the presence of a missing covariate. Based on simulation results, the proposed method shows a better performance than other simple imputation methods. ACTG 181 dataset were analyzed as a real example.

• Communications for Statistical Applications and Methods
• /
• 제19권5호
• /
• pp.721-729
• /
• 2012

Various methods control the influence of a covariate on a response variable. These methods are analysis of covariance(ANCOVA), RANK ANCOVA, ANOVA of (covariate-adjusted) residuals, and Kruskal-Wallis tests on residuals. Covariate-adjusted residuals are obtained from the overall regression line fit to the entire data set that ignore the treatment levels or factors. It is demonstrated that the methods on covariate-adjusted residuals are only appropriate when the regression lines are parallel and covariate means are equal for all treatments. In this paper, we proposed the new nonparametric method on the ANCOVA model, as applying joint placement in a one-way layout on residuals as described in Chung and Kim (2007). A Monte Carlo simulation study is adapted to compare the power of the proposed procedure with those of the previous procedure.

• 응용통계연구
• /
• 제25권3호
• /
• pp.521-529
• /
• 2012

Simple canonical correlation biplot is a graphical method to investigate two sets of variables and observations in simple canonical correlation analysis. If we consider the set of covariate variables that linearly affects two sets of variables, we can apply the partial canonical correlation biplot in partial canonical correlation analysis that removes the linear effect of the set of covariate variables on two sets of variables. On the other hand, we consider the set of covariate variables that linearly affect one set of variables but not the other. In this case, if we apply the simple or partial canonical correlation biplot, we cannot clearly interpret other two sets of variables. Therefore, in this study, we will apply the semi-partial canonical correlation analysis of Timm (2002) and remove the linear effect of the set of covariate variables on one set of variables but not the other. And we suggest the semi-partial canonical correlation biplot for interpreting the semi-partial canonical correlation analysis. In addition, we will compare shapes and shape the variabilities of the simple, partial and semi-partial canonical correlation biplots using a procrustes analysis.

• 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
• /
• 제13권2호
• /
• pp.31-38
• /
• 2002

In the case of multiple survival times which might be censored at each covariate vector, we study the regression quantile estimations in this paper. The estimations are based on the empirical distribution functions of the censored times and the sample quantiles of the observed survival times at each covariate vector and the weighted least square method is applied for the estimation of the regression quantile. The estimators are shown to be asymptotically normally distributed under some regularity conditions.

• Communications for Statistical Applications and Methods
• /
• 제4권2호
• /
• pp.491-496
• /
• 1997

For the survival data analysis of no covariate the discount survival model is proposed to estimate the time-varying hazard rate and the survival function recursively. In comparison with the covariate case it provide the distributionally explicit evolution of hazard rate between time intervals under the assumption of a conjugate gamma distribution. Also forecasting of the hazard rate in the next time interval is suggested, which leads to the forcecasted survival function.

• Communications for Statistical Applications and Methods
• /
• 제15권5호
• /
• pp.727-735
• /
• 2008

Consider a clinical trial in which the main end-point is survival. Suppose after the start of the study an intermediate event occurs which may be influenced by a covariate(or treatment). In many clinical studies the occurrence of an intermediate event may change the survival distribution. This investigation develops two-stage model which, in the first stage, models the effect of covariate on the intermediate event and models the relationship between survival time and covariate as well as the intermediate event. In this paper, the two-stage model is presented in order to model intermediate event and a test based on this model is also provided. A numerical simulations are carried out to evaluate its overall significance level.