R语言生存分析大全.docx

1、R语言生存分析大全CRAN Task View: Survival AnalysisMaintainer:Arthur Allignol and AurelienLatoucheContact:arthur.allignol at uni-ulm.deVersion:2016-01-27Survival analysis, also called event history analysis in social science, or reliability analysis in engineering, deals with time until occurrence of an even

2、t 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 themaintainersknow if something is inaccurate or missing.

3、Standard Survival AnalysisEstimation of the Survival Distribution Kaplan-Meier:Thesurvfitfunction from thesurvivalpackage computes the Kaplan-Meier estimator for truncated and/or censored data.rms(replacement of the Design package) proposes a modified version of thesurvfitfunction. Theprodlimpackage

4、 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.cipackage.plot.Survof packageehaplots the Kaplan-Meier estimator. TheNADApackage includes a function to compute the Kaplan

5、-Meier estimator for left-censored data.svykminsurveyprovides a weighted Kaplan-Meier estimator.nested.kminNestedCohortestimates the survival curve for each level of categorical variables with missing data. Thekaplan-meierfunction inspatstatcomputes the Kaplan-Meier estimator from histogram data. Th

6、eMAMSEpackage permits to compute a weighted Kaplan-Meier estimate. TheKMfunction in packagerhospplots the survival function using a variant of the Kaplan-Meier estimator in a hospitalisation risk context. ThesurvPresmoothpackage computes presmoothed estimates of the main quantities used for right-ce

7、nsored data, i.e., survival, hazard and density functions. Theasbiopackage permits to compute the Kaplan-Meier estimator following Pollock et al. (1998). Thebpcppackage provides several functions for computing confidence intervals of the survival distribution (e.g., beta product confidence procedure

8、). Thelbiassurvpackage offers various length-bias corrections to survival curve estimation. Non-Parametric confidance bands for the Kaplan-Meier estimator can be computed using thekmconfbandpackage. Thekmcpackage implements the Kaplan-Meier estimator with constraints. Non-Parametric maximum likeliho

9、od estimation (NPMLE):TheIcenspackage provides several ways to compute the NPMLE of the survival distribution for various censoring and truncation schemes.MLEcenscan also be used to compute the MLE for interval-censored data.dblcenspermits to compute the NPMLE of the cumulative distribution function

10、 for left- and right-censored data. Theicfitfunction in packageintervalcomputes the NPMLE for interval-censored data. TheDTDAimplements several algorithms permitting to analyse possibly doubly truncated survival data. Parametric:Thefitdistrpluspackage permits to fit an univariate distribution by max

11、imum likelihood. Data can be interval censored. Thevitalitypackage provides routines for fitting models in the vitality family of mortality models.Hazard Estimation Themuhazpackage permits to estimate the hazard function through kernel methods for right-censored data. Theepi.insthazfunction fromepiR

12、computes the instantaneous hazard from the Kaplan-Meier estimator. polspline,gssandlogsplineallow to estimate the hazard function using splines. TheICEpackage aims at estimating the hazard function for interval censored data. Thebshazardpackage provides non-parametric smoothing of the hazard through

13、 B-splines.Testing Thesurvdifffunction insurvivalcompares survival curves using the Fleming-Harrington G-rho family of test.NADAimplements this class of tests for left-censored data. clinfunimplements a permutation version of the logrank test and a version of the logrank that adjusts for covariates.

14、 TheexactRankTestsimplements the shift-algorithm by Streitberg and Roehmel for computing exact conditional p-values and quantiles, possibly for censored data. SurvTestin thecoinpackage implements the logrank test reformulated as a linear rank test. Themaxstatpackage performs tests using maximally se

15、lected rank statistics. Theintervalpackage implements logrank and Wilcoxon type tests for interval-censored data. Three generalisedlogrank tests and a score test for interval-censored data are implemented in theglrtpackage. survcompcompares 2 hazard ratios. TheTSHRCimplements a two stage procedure f

16、or comparing hazard functions. TheSurvginipackage proposes to test the equality of two survival distributions based on the Gini index. TheFHtestpackage offers several tests based on the Fleming-Harrington class for comparing surival curves with right- and interval-censored data. TheLogrankApackage p

17、rovides a logrank test for which aggregated data can be used as input. The short term and long term hazard ratio model for two samples survival data can be found in theYPmodelpackage.Regression Modelling Cox model:Thecoxphfunction in thesurvivalpackage fits the Cox model.cphin thermspackage and thee

18、hapackage propose some extensions to thecoxphfunction. The packagecoxphfimplements the Firths penalised maximum likelihood bias reduction method for the Cox model. An implementation of weighted estimation in Cox regression can be found incoxphw. Thecoxrobustpackage proposes a robust implementation o

19、f the Cox model.timecoxin packagetimeregfits Cox models with possibly time-varying effects. Themfppackage permits to fit Cox models with multiple fractional polynomial. TheNestedCohortfits Cox models for covariates with missing data. A Cox model model can be fitted to data from complex survey design

20、 using thesvycoxphfunction insurvey. ThemultipleNCCpackage fits Cox models using a weighted partial likelihood for nested case-control studies. Theintcoxpackage implements the Cox model for interval-censored data using the ICM-algorithm. TheMIICDpackage implements Pans (2000) multiple imputation app

21、roach to Cox models for interval censored data. TheICsurvpackage fits Cox models for interval-censored data through an EM algorithm. Thedynsurvpackage 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

22、 transformation model. TheCPHshapepackage computes the Cox proportional hazards model with shape constrained hazard functions. TheOrdFacRegpackage implements the Cox model using an active set algorithm for dummy variables of ordered factors. ThesurvivalMPLpackage fits Cox models using maximum penali

23、sed likelihood and provide a non parametric smooth estimate of the baseline hazard function.Thecumresfunction ingofcomputes goodness-of-fit methods for the Cox proportional hazards model. The proportionality assumption can be checked using thecox.zphfunction insurvival. TheCPEpackage calculates conc

24、ordance probability estimate for the Cox model, as does thecoxphCPEfunction inclinfun. ThecoxphQuantilein the latter package draws a quantile curve of the survival distribution as a function of covariates. Themultcomppackage computes simultaneous tests and confidence intervals for the Cox model and

25、other parametric survival models. Thelsmeanspackage permits to obtain least-squares means (and contrasts thereof) from linear models. In particular, it provides support for thecoxph,survregandcoxmefunctions. Themulttestpackage on Bioconductor proposes a resampling based multiple hypothesis testing t

26、hat 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 thesawspackage. Therankhazardpackage permits to plot visualisation of the relative importance of covariates in a proportional hazards model. Th

27、esmoothHRpackage provides hazard ratio curves that allows for nonlinear relationship between predictor and survival. Thepafpackage permits to compute the unadjusted/adjusted attributable fraction function from a Cox proportional hazards model. ThePHevalpackage proposes tools to check the proportiona

28、l hazards assumption using a standardised score process. Parametric Proportional Hazards Model:survreg(fromsurvival) fits a parametric proportional hazards model. TheehaandmixPHMpackages implement a proportional hazards model with a parametric baseline hazard. Thepphsminrmstranslates an AFT model to

29、 a proportional hazards form. Thepolsplinepackage includes theharefunction that fits a hazard regression model, using splines to model the baseline hazard. Hazards can be, but not necessarily, proportional. Theflexsurvpackage implements the model of Royston and Parmar (2002). The model uses natural

30、cubic splines for the baseline survival function, and proportional hazards, proportional odds or probit functions for regression. Accelerated Failure Time (AFT) Models:Thesurvregfunction in packagesurvivalcan fit an accelerated failure time model. A modified version ofsurvregis implemented in therms

31、package (psmfunction). It permits to use some of thermsfunctionalities. Theehapackage also proposes an implementation of the AFT model (functionaftreg). An AFT model with an error distribution assumed to be a mixture of G-splines is implemented in thesmoothSurvpackage. TheNADApackage proposes the fr

32、ont end of thesurvregfunction for left-censored data. A least-square principled implementation of the AFT model can be found in thelsspackage. Thesimexaftpackage 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 f