Movatterモバイル変換

CRAN Task View: Survival Analysis

Survival analysis, also called event history analysis in social science, or reliability analysis in engineering, deals with time until occurrence of an event of interest. However, this failure time may not be observed within the relevant time period, producing so-called censored observations.

This task view aims at presenting the useful R packages for the analysis of time to event data.

Please let the maintainers know if something is inaccurate or missing, either via e-mail or by submitting an issue or pull request in the GitHub repository linked above.

Standard Survival Analysis

Estimation of the Survival Distribution

• Kaplan-Meier: Thesurvfit function from thesurvival package computes the Kaplan-Meier estimator for truncated and/or censored data.rms (replacement of the Design package) proposes a modified version of thesurvfit function. Theprodlim package implements a fast algorithm and some features not included insurvival. Various confidence intervals and confidence bands for the Kaplan-Meier estimator are implemented in thekm.ci package.plot.Surv of packageeha plots the Kaplan-Meier estimator. TheNADA package includes a function to compute the Kaplan-Meier estimator for left-censored data.svykm insurvey provides a weighted Kaplan-Meier estimator. Thekaplan-meier function inspatstat computes the Kaplan-Meier estimator from histogram data. TheKM function in packagerhosp(archived) plots the survival function using a variant of the Kaplan-Meier estimator in a hospitalisation risk context. ThesurvPresmooth package computes presmoothed estimates of the main quantities used for right-censored data, i.e., survival, hazard and density functions. Theasbio package permits to compute the Kaplan-Meier estimator following Pollock et al. (1998). Thebpcp package provides several functions for computing confidence intervals of the survival distribution (e.g., beta product confidence procedure). Thekmc package implements the Kaplan-Meier estimator with constraints. Thelandest package allows landmark estimation and testing of survival probabilities. ThecondSURV package provides methods for estimating the conditional survival function for ordered multivariate failure time data. Thegte package implements the generalised Turnbull estimator proposed by Dehghan and Duchesne for estimating the conditional survival function with interval-censored data.

• Non-Parametric maximum likelihood estimation (NPMLE): The
  Icens package provides several ways to compute the NPMLE of the survival distribution for various censoring and truncation schemes.MLEcens can also be used to compute the MLE for interval-censored data.dblcens permits to compute the NPMLE of the cumulative distribution function for left- and right-censored data. Theicfit function in packageinterval computes the NPMLE for interval-censored data. TheDTDA package implements several algorithms permitting to analyse possibly doubly truncated survival data.
  npsurv computes the NPMLE of a survival function for general interval-censored data. Thecsci package provides confidence intervals for the cumulative distribution function of the event time for current status data, including a new method that is valid (i.e., exact).

• Parametric: Thefitdistrplus package permits to fit an univariate distribution by maximum likelihood. Data can be interval censored. Thevitality package provides routines for fitting models in the vitality family of mortality models.

Hazard Estimation

• Themuhaz package permits to estimate the hazard function through kernel methods for right-censored data.
• Theepi.insthaz function fromepiR computes the instantaneous hazard from the Kaplan-Meier estimator.
• polspline,gss andlogspline allow to estimate the hazard function using splines.
• Thebshazard package provides non-parametric smoothing of the hazard through B-splines.

Testing

• Thesurvdiff function insurvival compares survival curves using the Fleming-Harrington G-rho family of test.NADA implements this class of tests for left-censored data.
• Themaxcombo package compares survival curves using the max-combo test, which is often based on the Fleming-Harrington G-rho family of tests and is designed to have higher power than the logrank test in the scenario of non-proportional hazards such as those resulting from delayed treatment effects.
• clinfun implements a permutation version of the logrank test and a version of the logrank that adjusts for covariates.
• TheexactRankTests implements the shift-algorithm by Streitberg and Roehmel for computing exact conditional p-values and quantiles, possibly for censored data.
• SurvTest in thecoin package implements the logrank test reformulated as a linear rank test.
• Themaxstat package performs tests using maximally selected rank statistics.
• Theinterval package implements logrank and Wilcoxon type tests for interval-censored data.
• survcomp compares 2 hazard ratios.
• TheTSHRC implements a two stage procedure for comparing hazard functions.
• TheFHtest package offers several tests based on the Fleming-Harrington class for comparing surival curves with right- and interval-censored data.
• The short term and long term hazard ratio model for two samples survival data can be found in theYPmodel package.
• ThecontrolTest implements a nonparametric two-sample procedure for comparing the median survival time.
• ThesurvRM2 package performs two-sample comparison of the restricted mean survival time
• Theemplik2 package permits to compare two samples with censored data using empirical likelihood ratio tests.
• TheKONPsurv package provides powerful nonparametric K-sample tests for right-censored data. The tests are consistent against any differences between the hazard functions of the groups.

Regression Modelling

• Cox model: Thecoxph function in thesurvival package fits the Cox model.cph in therms package and theeha package propose some extensions to thecoxph function. The packagecoxphf implements the Firth’s penalised maximum likelihood bias reduction method for the Cox model. An implementation of weighted estimation in Cox regression can be found incoxphw. Thecoxrobust package proposes a robust implementation of the Cox model.timecox in packagetimereg fits Cox models with possibly time-varying effects. A Cox model model can be fitted to data from complex survey design using thesvycoxph function insurvey. ThemultipleNCC package fits Cox models using a weighted partial likelihood for nested case-control studies. TheICsurv package fits Cox models for interval-censored data through an EM algorithm. Thedynsurv package fits time-varying coefficient models for interval censored and right censored survival data using a Bayesian Cox model, a spline based Cox model or a transformation model. TheOrdFacReg package implements the Cox model using an active set algorithm for dummy variables of ordered factors. ThesurvivalMPL package fits Cox models using maximum penalised likelihood and provide a non parametric smooth estimate of the baseline hazard function. A Cox model with piecewise constant hazards can be fitted using thepch package. TheicenReg package implements several models for interval-censored data, e.g., Cox, proportional odds, and accelerated failure time models. A Cox type Self-Exciting Intensity model can be fitted to right-censored data using thecoxsei package. TheSurvLong contains methods for estimation of proportional hazards models with intermittently observed longitudinal covariates. Theplac package provides routines to fit the Cox model with left-truncated data using augmented information from the marginal of the truncation times. Theboot.pval package contains the convenience functioncensboot_summary for computing bootstrap p-values and confidence intervals for Cox models.
  The proportionality assumption can be checked using thecox.zph function insurvival. ThecoxphCPE function inclinfun calculates concordance probability estimate for the Cox model. ThecoxphQuantile in the latter package draws a quantile curve of the survival distribution as a function of covariates. Themultcomp package computes simultaneous tests and confidence intervals for the Cox model and other parametric survival models. Thelsmeans package permits to obtain least-squares means (and contrasts thereof) from linear models. In particular, it provides support for thecoxph,survreg andcoxme functions. Themulttest package on Bioconductor proposes a resampling based multiple hypothesis testing that can be applied to the Cox model. Testing coefficients of Cox regression models using a Wald test with a sandwich estimator of variance can be done using thesaws package. Therankhazard package permits to plot visualisation of the relative importance of covariates in a proportional hazards model. ThesmoothHR package provides hazard ratio curves that allows for nonlinear relationship between predictor and survival. ThePHeval package proposes tools to check the proportional hazards assumption using a standardised score process. TheELYP package implements empirical likelihood analysis for the Cox Model and Yang-Prentice (2005) Model.
• Parametric Proportional Hazards Model:survreg (fromsurvival) fits a parametric proportional hazards model. Theeha andmixPHM packages implement a proportional hazards model with a parametric baseline hazard. Thepphsm inrms translates an AFT model to a proportional hazards form. Thepolspline package includes thehare function that fits a hazard regression model, using splines to model the baseline hazard. Hazards can be, but not necessarily, proportional. Theflexsurv package implements the model of Royston and Parmar (2002). The model uses natural cubic splines for the baseline survival function, and proportional hazards, proportional odds or probit functions for regression. TheSurvRegCensCov package allows estimation of a Weibull Regression for a right-censored endpoint, one interval-censored covariate, and an arbitrary number of non-censored covariates.
• Accelerated Failure Time (AFT) Models: Thesurvreg function in packagesurvival can fit an accelerated failure time model. A modified version ofsurvreg is implemented in therms package (psm function). It permits to use some of therms functionalities. Theeha package also proposes an implementation of the AFT model (functionaftreg). TheNADA package proposes the front end of thesurvreg function for left-censored data. Thesimexaft(archived) package implements the Simulation-Extrapolation algorithm for the AFT model, that can be used when covariates are subject to measurement error. A robust version of the accelerated failure time model can be found inRobustAFT. ThecoarseDataTools package fits AFT models for interval censored data. Theaftgee package implements recently developed inference procedures for the AFT models with both the rank-based approach and the least squares approach. Theboot.pval package contains the convenience functioncensboot_summary for computing bootstrap p-values and confidence intervals for AFT models.
• Additive Models: Bothsurvival andtimereg fit the additive hazards model of Aalen in functionsaareg andaalen, respectively.timereg also proposes an implementation of the Cox-Aalen model (that can also be used to perform the Lin, Wei and Ying (1994) goodness-of-fit for Cox regression models) and the partly parametric additive risk model of McKeague and Sasieni. Theuniah package fits shape-restricted additive hazards models. Theaddhazard package contains tools to fit additive hazards model to random sampling, two-phase sampling and two-phase sampling with auxiliary information.
• Buckley-James Models: Thebj function inrms andBJnoint inemplik compute the Buckley-James model, though the latter does it without an intercept term. Thebujar package fits the Buckley-James model with high-dimensional covariates (L2 boosting, regression trees and boosted MARS, elastic net).
• Other models: Functions likesurvreg can fit other types of models depending on the chosen distribution,e.g. , a tobit model. TheAER package provides thetobit function, which is a wrapper ofsurvreg to fit the tobit model. An implementation of the tobit model for cross-sectional data and panel data can be found in thecensReg package. Ther pkg("timereg") package provides implementation of the proportional odds model and of the proportional excess hazards model. TheinvGauss package fits the inverse Gaussian distribution to survival data. The model is based on describing time to event as the barrier hitting time of a Wiener process, where drift towards the barrier has been randomized with a Gaussian distribution. Thepseudo package computes the pseudo-observation for modelling the survival function based on the Kaplan-Meier estimator and the restricted mean.r pkg("flexsurv") fits parametric time-to-event models, in which any parametric distribution can be used to model the survival probability, and where any of the parameters can be modelled as a function of covariates. TheIcens function in packager pkg("Epi") provides a multiplicative relative risk and an additive excess risk model for interval-censored data. Ther pkg("VGAM") package can fit vector generalised linear and additive models for censored data. Thegamlss.cens package implements the generalised additive model for location, scale and shape that can be fitted to censored data. Thelocfit.censor function inlocfit produces local regression estimates. Thecrq function included in ther pkg("quantreg") package implements a conditional quantile regression model for censored data. TheJM package fits shared parameter models for the joint modelling of a longitudinal response and event times. The temporal process regression model is implemented in thetpr package. Aster models, which combine aspects of generalized linear models and Cox models, are implemented in theaster andaster2 packages. Thesurv2sampleComp packages proposes some model-free contrast comparison measures such as difference/ratio of cumulative hazards, quantiles and restricted mean. Ther pkg("rstpm2") package provides link-based survival models that extend the Royston-Parmar models, a family of flexible parametric models. TheTransModel package implements a unified estimation procedure for the analysis of censored data using linear transformation models. TheICGOR fits the generalized odds rate hazards model to interval-censored data whileGORCure generalized odds rate mixture cure model to interval-censored data. ThethregI package permits to fit a threshold regression model for interval-censored data based on the first-hitting-time of a boundary by the sample path of a Wiener diffusion process. ThemiCoPTCM package fits semiparametric promotion time cure models with possibly mis-measured covariates. Thesmcure package permits to fit semiparametric proportional hazards and accelerated failure time mixture cure models. The case-base sampling approach for fitting flexible hazard regression models to survival data with single event type or multiple competing causes via logistic and multinomial regression can be found in packager pkg("casebase"). Theintsurv package fits regular Cox cure rate model via an EM algorithm, regularized Cox cure rate model with elastic net penalty, and weighted concordance index for cure models. TheGJRM package supports univariate proportional hazard, proportional odds and probit link models where the baseline and many types of covariate effects (including spatial and time-dependent effects) are modelled flexibly by means of penalised smoothers (e.g., penalised thin plate, monotonic B- and cubic splines, tensor products and Markov random fields). Right, left and interval censoring and left truncation can also be accounted for. This is done through the functiongamlss. The packagetram allows a range of stratified linear transformation models to be fitted, among them Cox models and other parametric models. It allows to also estimate flexible survival models for interval-censored data in a straightforward manner, and has many useful extensions. Modeling periodic mortality (or other time-to event) processes from right-censored data can be done using thecyclomort package.

Multistate Models

• General Multistate Models: Thecoxph function from packagesurvival can be fitted for any transition of a multistate model. It can also be used for comparing two transition hazards, using correspondence between multistate models and time-dependent covariates. Besides, all the regression methods presented above can be used for multistate models as long as they allow for left-truncation. Themvna package provides convenient functions for estimating and plotting the cumulative transition hazards in any multistate model, possibly subject to right-censoring and left-truncation. Theetm package estimates and plots transition probabilities for any multistate models. It can also estimate the variance of the Aalen-Johansen estimator, and handles left-truncated data. Themstate package permits to estimate hazards and probabilities, possibly depending on covariates, and to obtain prediction probabilities in the context of competing risks and multistate models. Theflexsurv package can fit and predict from fully-parametric multistate models, with arbitrarily-flexible time-to-event distributions, using either a cause-specific hazards or mixture model framework. Themsm package contains functions for fitting general continuous-time Markov and hidden Markov multistate models to longitudinal data. Transition rates and output processes can be modelled in terms of covariates. Theflexmsm package provides a general estimation framework for multi-state Markov processes with flexible specification of the transition intensities. It supports any type of process structure (forward and backward transitions, any number of states) and transition intensities can be specified via Generalised Additive Models, with syntax similar to that used for GAMs in R. TheSemiMarkov package can be used to fit semi-Markov multistate models in continuous time. The distribution of the waiting times can be chosen between the exponential, the Weibull and exponentiated Weibull distributions. TheTPmsm package permits to estimate transition probabilities of an illness-death model or three-state progressive model. ThegamboostMSM(archived) package extends themboost package to estimation in the mulstistate model framework, while thepenMSM package proposes L1 penalised estimation. TheTP.idm(archived) package implement the estimator of Una-Alvarez and Meira-Machado (2015) for non-Markov illness-death models.
  TheEpi package implements Lexis objects as a way to represent, manipulate and summarise data from multistate models. TheLexisPlotR package, based onggplot2 , permits to draw Lexis diagrams. TheTraMineR package is intended for analysing state or event sequences that describe life courses.asbio computes the expected numbers of individuals in specified age classes or life stages given survivorship probabilities from a transition matrix.
• Competing risks: The packagecmprsk estimates the cumulative incidence functions, but they can be compared in more than two samples. The package also implements the Fine and Gray model for regressing the subdistribution hazard of a competing risk.crrSC extends thecmprsk package to stratified and clustered data. Thekmi package performs a Kaplan-Meier multiple imputation to recover missing potential censoring information from competing risks events, permitting to use standard right-censored methods to analyse cumulative incidence functions. Packagepseudo computes pseudo observations for modelling competing risks based on the cumulative incidence functions.timereg does flexible regression modelling for competing risks data based on the on the inverse-probability-censoring-weights and direct binomial regression approach.riskRegression implements risk regression for competing risks data, along with other extensions of existing packages useful for survival analysis and competing risks data. Packagessurvival (viasurvfit) andprodlim can also be used to estimate the cumulative incidence function. TheNPMLEcmprsk package implements the semi-parametric mixture model for competing risks data. TheCFC package permits to perform Bayesian, and non-Bayesian, cause-specific competing risks analysis for parametric and non-parametric survival functions. Thegcerisk package provides some methods for competing risks data. Estimation, testing and regression modeling of subdistribution functions in the competing risks setting using quantile regressions can be had incmprskQR. Theintccr package permits to fit the Fine and Gray model as well other models that belong to the class of semiparametric generalized odds rate transformation models to interval-censored competing risks data. Themmcif(archived) fits mixed cumulative incidence function models to model within-cluster dependence of both risk and timing.
• Recurrent event data:coxph from thesurvival package can be used to analyse recurrent event data. Thecph function of therms package fits the Anderson-Gill model for recurrent events, model that can also be fitted with thefrailtypack package. The latter also permits to fit joint frailty models for joint modelling of recurrent events and a terminal event. ThecondGEE package implements the conditional GEE for recurrent event gap times. Thereda package provides function to fit gamma frailty model with either a piecewise constant or a spline as the baseline rate function for recurrent event data, as well as some miscellaneous functions for recurrent event data. Several regression models for recurrent event data are implemented in thereReg package. Thespef package includes functions for fitting semiparametric regression models for panel count survival data.

Relative Survival

• Therelsurv package proposes several functions to deal with relative survival data. For example,rs.surv computes a relative survival curve.rs.add fits an additive model andrsmul fits the Cox model of Andersen et al. for relative survival, whilerstrans fits a Cox model in transformed time.
• Thetimereg package permits to fit relative survival models like the proportional excess and additive excess models.
• Themexhaz package allows fitting an hazard regression model using different shapes for the baseline hazard. The model can be used in the relative survival setting (excess mortality hazard) as well as in the overall survival setting (overall mortality hazard).
• Theflexrsurv package implements the models of Remontet et al. (2007) and Mahboubi et al. (2011).
• Thesurvexp.fr package computes relative survival, absolute excess risk and standardized mortality ratio based on French death rates.
• TheGJRM package permits to fit link-based additive models for the excess hazard that allows for the inclusion of many types of covariate effects, including spatial and time-dependent effects, using any type of smoother, such as thin plate, cubic splines, tensor products and Markov random fields. Informative censoring can be accounted for as well as in the above.
• Thexhaz fits relative survival regression models with or without proportional excess hazards and with the additional possibility to correct for background mortality by one or more parameters.

Random Effect Models

• Frailties: Frailty terms can be added incoxph function in packagesurvival. A mixed-effects Cox model is implemented in thecoxme package. Thetwo.stage function in thetimereg package fits the Clayton-Oakes-Glidden model. Thefrailtypack package fits proportional hazards models with a shared Gamma frailty to right-censored and/or left-truncated data using a penalised likelihood on the hazard function. The package also fits additive and nested frailty models that can be used for, e.g., meta-analysis and for hierarchically clustered data (with 2 levels of clustering), respectively. The Cox model using h-likelihood estimation for the frailty terms can be fitted using thefrailtyHL package. ThefrailtySurv package simulates and fits semiparametric shared frailty models under a wide range of frailty distributions. ThePenCoxFrail package provides a regularisation approach for Cox frailty models through penalisation. Themexhaz enables modelling of the excess hazard regression model with time-dependent and/or non-linear effect(s) and a random effect defined at the cluster level. ThefrailtyEM package contains functions for fitting shared frailty models with a semi-parametric baseline hazard with the Expectation-Maximization algorithm. Supported data formats include clustered failures with left truncation and recurrent events in gap-time or Andersen-Gill format
• Joint modelling of time-to-event and longitudinal data: ThejoineR package allows the analysis of repeated measurements and time-to-event data via joint random effects models. Thejoint.Cox package performs Cox regression and dynamic prediction under the joint frailty-copula model between tumour progression and death for meta-analysis. ThejoineRML package fits the joint model proposed by Henderson and colleagues (2000)doi:10.1093/biostatistics/1.4.465 , but extended to the case of multiple continuous longitudinal measures. Therstanarm package fits joint models for one or more longitudinal outcomes (continuous, binary or count data) and a time-to-event, estimated under a Bayesian framework.

Multivariate Survival

Multivariate survival refers to the analysis of unit, e.g., the survival of twins or a family. To analyse such data, we can estimate the joint distribution of the survival times

• Joint modelling: BothIcens andMLEcens can estimate bivariate survival data subject to interval censoring.
• Themets package implements various statistical models for multivariate event history data, e.g., multivariate cumulative incidence models, bivariate random effects probit models, Clayton-Oakes model.
• TheMST package constructs trees for multivariate survival data using marginal and frailty models.
• TheSurvCorr package permits to estimate correlation coefficients with associated confidence limits for bivariate, partially censored survival times.
• TheMultSurvTests package contains multivariate versions of the two-sample Gehan and logrank tests.
• TheGJRM package supports flexible joint modelling of bivariate survival outcomes by means of copulae. Several types of covariate effects, copulae and marginal distributions are allowed.

Bayesian Models

• The packageBMA computes a Bayesian model averaging for Cox proportional hazards models.
• NMixMCMC inmixAK performs an MCMC estimation of normal mixtures for censored data.
• A MCMC for Gaussian linear regression with left-, right- or interval-censored data can be fitted using theMCMCtobit inMCMCpack.
• Theweibullregpost function inLearnBayes computes the log posterior density for a Weibull proportional-odds regression model.
• TheMCMCglmm fits generalised linear mixed models using MCMC to right-, left- and interval censored data.
• TheJMbayes package performs joint modelling of longitudinal and time-to-event data under a bayesian approach.
• Therstanarm package fits a joint model for one or more longitudinal outcomes (continuous, binary or count data) and a time-to-event under a Bayesian framework.
• Bayesian parametric and semi-parametric estimation for semi-competing risks data is available via theSemiCompRisks package.
• ThepsbcGroup package implements penalized semi-parametric Bayesian Cox models with elastic net, fused lasso and group lasso priors. ThepsbcSpeedUp package proposes faster implementation of the latter.
• ThePReMiuM package implements Bayesian clustering using a Dirichlet process mixture model to censored responses.
• ThespBayesSurv package provides Bayesian model fitting for several survival models including spatial copula, linear dependent Dirichlet process mixture model, anova Dirichlet process mixture model, proportional hazards model and marginal spatial proportional hazards model.
• TheIDPSurvival package implements non-parametric survival analysis techniques using a prior near-ignorant Dirichlet Process.
• TheBayesSurvive package implements Bayesian survival models with graph-structured selection priors for sparse identification of omics features predictive of survival
• The packagesurvival.svb uses a spike-and-slab prior with Laplace slab and Dirac spike to allow variable selection, effect estimation, and uncertainty quantification, for high-dimensional survival data.
• Parametric survival regression models (proportional hazards, AFTs) using stan can be fitted with packagesurvstan.

Machine learning

• Recursive partitioning:rpart implements CART-like trees that can be used with censored outcomes. Theparty package implements recursive partitioning for survival data.LogicReg can perform logic regression. TheLTRCtrees package provides recursive partition algorithms designed for fitting survival tree with left-truncated and right censored data. The package also includes an implementation of recursive partitioning (conditional inference trees) for interval-censored data.bnnSurvival implements a bootstrap aggregated version of the k-nearest neighbors survival probability prediction method.
• Random forest: Packageipred implements bagging for survival data. TherandomForestSRC package fits random forest to survival data, while a variant of the random forest is implemented inparty. A faster implementation can be found in packageranger. An alternative algorithm for random forests is implemented inicRSF.
• Regularised and shrinkage methods: Theglmnet package provides procedures for fitting the entire lasso or elastic-net regularization path for Cox models. Theglmpath package implements a L1 regularised Cox proportional hazards model. An L1 and L2 penalised Cox models are available inpenalized. Thepamr package computes a nearest shrunken centroid for survival gene expression data. Thelpc package implements the lassoed principal components method. Theahaz package implements the LASSO and elastic net estimator for the additive risk model. Thefastcox package implements the Lasso and elastic-net penalized Cox’s regression using the cockail algorithm. TheSGL package permits to fit Cox models with a combination of lasso and group lasso regularisation. Thehdnom package implements 9 types of penalised Cox regression methods and provides methods for model validation, calibration, comparison, and nomogram visualisation. TheCyclops package implements cyclic coordinate descent for the Cox proportional hazards model.
• Boosting: Gradient boosting for the Cox model is implemented in thegbm package. Themboost package includes a generic gradient boosting algorithm for the construction of prognostic and diagnostic models for right-censored data.xgboost includes methods for Cox regression (right censored survival data) and AFT models (right-, left-, interval-, and uncensored).
• Other: Thesuperpc package implements the supervised principal components for survival data. Thecompound.Cox package fits Cox proportional hazards model using the compound covariate method.plsRcox provides partial least squares regression and various techniques for fitting Cox models in high dimensionnal settings.

Predictions and Prediction Performance

• Thepec package provides utilities to plot prediction error curves for several survival models. TheriskRegression package now includes most of the functionality of thepec package.
• peperr implements prediction error techniques which can be computed in a parallelised way. Useful for high-dimensional data.
• ThetimeROC package permits to estimate time-dependent ROC curves and time-dependent AUC with censored data, possibly with competing risks.
• survivalROC computes time-dependent ROC curves and time-dependent AUC from censored data using Kaplan-Meier or Akritas’s nearest neighbour estimation method (Cumulative sensitivity and dynamic specificity).
• tdROC can be used to compute time-dependent ROC curve from censored survival data using nonparametric weight adjustments.
• risksetROC implements time-dependent ROC curves, AUC and integrated AUC of Heagerty and Zheng (Biometrics, 2005).
• Various time-dependent true/false positive rates and Cumulative/Dynamic AUC are implemented in thesurvAUC package.
• Thesurvcomp package provides several functions to assess and compare the performance of survival models.
• C-statistics for risk prediction models with censored survival data can be computed via thesurvC1 package.
• ThesurvIDINRI package implements the integrated discrimination improvement index and the category-less net reclassification index for comparing competing risks prediction models.
• ThecompareC package permits to compare C indices with right-censored survival outcomes
• TheAPtools package provide tools to estimate the average positive predictive values and the AUC for risk scores or marker.

Power Analysis

• TheNPHMC permits to calculate sample size based on proportional hazards mixture cure models.
• ThepowerSurvEpi package provides power and sample size calculation for survival analysis (with a focus towards epidemiological studies).
• Power analysis and sample size calculation for SNP association studies with time-to-event outcomes can be done using thesurvSNP package.

Simulation

• ThegenSurv package permits to generate data wih one binary time-dependent covariate and data stemming from a progressive illness-death model.
• ThePermAlgo package permits the user to simulate complex survival data, in which event and censoring times could be conditional on an user-specified list of (possibly time-dependent) covariates.
• Theprodlim package proposes some functions for simulating complex event history data.
• Thegems package also permits to simulate and analyse multistate models. The package allows for a general specification of the transition hazard functions, for non-Markov models and for dependencies on the history.
• ThesimMSM package provides functions for simulating complex multistate models data with possibly nonlinear baseline hazards and nonlinear covariate effects.
• ThesimPH package implements tools for simulating and plotting quantities of interest estimated from proportional hazards models.
• Thesurvsim package permits to simulate simple and complex survival data such as recurrent event data and competing risks.
• Thesimsurv package enables the user to simulate survival times from standard parametric survival distributions (exponential, Weibull, Gompertz), 2-component mixture distributions, or a user-defined hazard or log hazard function. Time dependent effects (i.e. non-proportional hazards) can be included by interacting covariates with linear time or some transformation of time.
• TheMicSim package provides routines for performing continuous-time microsimulation for population projection. The basis for the microsimulation are a multistate model, Markov or non-Markov, for which the transition intensities are specified, as well as an initial cohort.
• TheSimHaz package permits to simulate data with a dichotomous time-dependent exposure.
• TheSimSurvNMarker package provides functions to simulate from joint survival and potentially multivariate marker models. User-defined basis expansions in time can be passed which effect the log hazard, the markers, and the association between the two.
• The R packagersurv permits to generate survival data from a wide range of regression models, including accelerated failure time, proportional hazards, proportional odds, accelerated hazard, Yang and Prentice, and extended hazard models.

Graphics

This section tries to list some specialised plot functions that might be useful in the context of event history analysis.

• Therms package proposes functions for plotting survival curves with the at risk table aligned to the x axis.prodlim extends this to the competing risks model.
• Theplot.Hist function inprodlim permits to draw the states and transitions that characterize a multistate model.
• TheEpi package provides many plot functions for representing multistate data, in particular Lexis diagrams.
• TheFamEvent generates time-to-event outcomes for families that habour genetic mutation under different sampling designs and estimates the penetrance functions for family data with ascertainment correction.
• vsd(archived) provides graphical shim for visual survival data analysis.

Miscellaneous

• Thesurvminer package contains the functionggsurvplot for drawing survival curves with the “number at risk” table. Other functions are also available for visual examinations of Cox model assumptions.
• TheInformativeCensoring package multiple imputation methods for dealing with informative censoring.
• ThediscSurv provides data transformations, estimation utilities, predictive evaluation measures and simulation functions for discrete time survival analysis.
• dynpred is the companion package to “Dynamic Prediction in Clinical Survival Analysis”.
• Packageboot proposes thecensboot function that implements several types of bootstrap techniques for right-censored data. Theboot.pval package contains the convenience functioncensboot_summary for computing bootstrap p-values and confidence intervals for Cox models and accelerated failure time models.
• ThecurrentSurvival package estimates the current cumulative incidence and the current leukaemia free survival function.
• TheKMsurv package includes the data sets from Klein and Moeschberger (1997). The packageSMPracticals that accompanies Davidson (2003) andDAAG that accompanies Maindonald, J.H. and Braun, W.J. (2003, 2007) also contain survival data sets.
• TheSvyNom package permits to construct, validate and calibrate nomograms stemming from complex right-censored survey data.
• Thelogconcens package compute the MLE of a density (log-concave) possibly for interval censored data.
• ThecoarseDataTools package implements an EM algorithm to estimate the relative case fatality ratio between two groups.
• TheGSSE package proposes a fully efficient sieve maximum likelihood method to estimate genotype-specific distribution of time-to-event outcomes under a nonparametric model
• power and sample size calculation based on the difference in restricted mean survival times can be performed using theSSRMST package.
• ThesurvMisc provides miscellaneous routines to help in the analysis of right-censored survival data.
• Accompanying data sets to the bookApplied Survival Analysis Using R can be found in packageasaur.
• Thesurvex provides easy-to-apply explanations of survival models (both complex machine learning and simpler statistical ones) that enable their exploration and interpretation.

CRAN packages

Related links

• GAMLSS
• Tutorial in competing risks and multistate models
• Proportional-Hazards Regression for Survival Data. Appendix to An R and S-PLUS Companion to Applied Regression.
• Journal of Statistical Software. Special Volume: Competing Risks and Multi-State Models

Other resources

• Bioconductor Package:Icens
• Bioconductor Package:multtest
• Bioconductor Package:survcomp