ROC curve is a popular graphical method frequently used in order to study the diagnostic capacity of continuous (bio)markers. When the considered outcome is a time-dependent variable, the direct generalization is known as cumulative/dynamic ROC curve. For a fixed point of time, t, one subject is allocated into the positive group if the event happens before t and into the negative group if the event is not happened at t. The presence of censored subject, which can not be directly assigned into a group, is the main handicap of this approach. The proposed cumulative/dynamic ROC curve estimator assigns a probability to belong to the negative (positive) group to the subjects censored previously to t. The performance of the resulting estimator is studied from Monte Carlo simulations. Some real-world applications are reported. Results suggest that the new estimators provide a good approximation to the real cumulative/dynamic ROC curve.

No abstract

Receiver operating-characteristic curve is a popular graphical method frequently used in order to study the diagnostic capacity of continuous (bio)markers. In spite of the existence of a huge number of papers devoted to both theoretical and practical aspects of this topic, the construction of confidence bands has had little impact in the specialized literature. As far as the authors know, in the CRAN there are only three R packages providing receiver operating-characteristic curve confidence regions: plotROC, pROC and fbroc. This work tries to fill this gap studying and proposing a new nonparametric method to build confidence bands for both the standard receiver operating-characteristic curve and its generalization for nonmonotone relationships. The behavior of the proposed procedure is studied via Monte Carlo simulations and the methodology is applied on two real-world biomedical problems. In addition, an R function to compute the proposed and some of the previously existing methodologies is provided as online supplementary material.

The receiver operating characteristic (ROC) curve is a graphical method which has become standard in the analysis of diagnostic markers, that is, in the study of the classification ability of a numerical variable. Most of the commercial statistical software provide routines for the standard ROC curve analysis. Of course, there are also many R packages dealing with the ROC estimation as well as other related problems. In this work we introduce the nsROC package which incorporates some new ROC curve procedures. Particularly: ROC curve comparison based on general distances among functions for both paired and unpaired designs; efficient confidence bands construction; a generalization of the curve considering different classification subsets than the one involved in the classical definition of the ROC curve; a procedure to deal with censored data in cumulative-dynamic ROC curve estimation for time-to-event outcomes; and a non-parametric ROC curve method for meta-analysis. This is the only R package which implements these particular procedures. Estimation Non-standard ROC curve estimationAs mentioned previously, an ROC curve is a graphical method which displays the sensitivity (Se) versus the complementary of the specificity (1-Sp) for all possible thresholds of the considered marker.Although different parametric and semi-parametric estimators for the ROC curve have been studied, in our package the empirical estimator, based on replacing the involved unknown distribution functions with their respective empirical cumulative distribution functions,F, has been considered. Hence, the implemented ROC curve estimator isAbstract The increase in life expectancy followed by the burden of chronic diseases contributes to disability at older ages. The estimation of how much chronic conditions contribute to disability can be useful to develop public health strategies to reduce the burden. This paper introduces the R package addhaz, which is based on the attribution method (Nusselder and Looman, 2004) to partition disability into the additive contributions of diseases using cross-sectional data. The R package includes tools to fit the additive hazard model, the core of the attribution method, to binary and multinomial outcomes. The models are fitted by maximizing the binomial and multinomial log-likelihood functions using constrained optimization. Wald and bootstrap confidence intervals can be obtained for the parameter estimates. Also, the contribution of diseases to the disability prevalence and their bootstrap confidence intervals can be estimated. An additional feature is the possibility to use parallel computing to obtain the bootstrap confidence intervals. In this manuscript, we illustrate the use of addhaz with several examples for the binomial and multinomial models, using the data from the Brazilian National Health Survey, 2013.

No abstract