Debian Codegraph @

man/probtrans.Rd

raw
1 % Generated by roxygen2: do not edit by hand
2 % Please edit documentation in R/probtrans.R
3 \name{probtrans}
4 \alias{probtrans}
5 \title{Compute subject-specific or overall transition probabilities with standard
6 errors}
7 \usage{
8 probtrans(
9 object,
10 predt,
11 direction = c("forward", "fixedhorizon"),
12 method = c("aalen", "greenwood"),
13 variance = TRUE,
14 covariance = FALSE
15 )
16 }
17 \arguments{
18 \item{object}{\link{msfit} object containing estimated cumulative hazards
19 for each of the transitions in the multi-state model and, if standard errors
20 are requested, (co)variances of these cumulative hazards for each pair of
21 transitions}
22
23 \item{predt}{A positive number indicating the prediction time. This is
24 either the time at which the prediction is made (if \code{direction}=
25 \code{"forward"}) or the time for which the prediction is to be made (if
26 \code{direction}=\code{"fixedhorizon"})}
27
28 \item{direction}{One of \code{"forward"} (default) or \code{"fixedhorizon"},
29 indicating whether prediction is forward or for a fixed horizon}
30
31 \item{method}{A character string specifying the type of variances to be
32 computed (so only needed if either \code{variance} or \code{covariance} is
33 \code{TRUE}). Possible values are \code{"aalen"} or \code{"greenwood"}}
34
35 \item{variance}{Logical value indicating whether standard errors are to be
36 calculated (default is \code{TRUE})}
37
38 \item{covariance}{Logical value indicating whether covariances of transition
39 probabilities for different states are to be calculated (default is
40 \code{FALSE})}
41 }
42 \value{
43 An object of class \code{"probtrans"}, which is a list of which item
44 [[s]] contains a data frame with the estimated transition probabilities (and
45 standard errors if \code{variance}=\code{TRUE}) from state s. If
46 \code{covariance}=\code{TRUE}, item \code{varMatrix} contains an array of
47 dimension K^2 x K^2 x (nt+1) (with K the number of states and nt the
48 distinct transition time points); the time points correspond to those in the
49 data frames with the estimated transition probabilities. Finally, there are
50 items \code{trans}, \code{method}, \code{predt}, \code{direction}, recording
51 the transition matrix, and the method, predt and direction arguments used in
52 the call to probtrans. Plot and summary methods have been defined for
53 \code{"probtrans"} objects.
54 }
55 \description{
56 This function computes subject-specific or overall transition probabilities
57 in multi-state models. If requested, also standard errors are calculated.
58 }
59 \details{
60 For details refer to de Wreede, Fiocco & Putter (2010).
61 }
62 \examples{
63
64 # transition matrix for illness-death model
65 tmat <- trans.illdeath()
66 # data in wide format, for transition 1 this is dataset E1 of
67 # Therneau & Grambsch (2000)
68 tg <- data.frame(illt=c(1,1,6,6,8,9),ills=c(1,0,1,1,0,1),
69 dt=c(5,1,9,7,8,12),ds=c(1,1,1,1,1,1),
70 x1=c(1,1,1,0,0,0),x2=c(6:1))
71 # data in long format using msprep
72 tglong <- msprep(time=c(NA,"illt","dt"),status=c(NA,"ills","ds"),
73 data=tg,keep=c("x1","x2"),trans=tmat)
74 # events
75 events(tglong)
76 table(tglong$status,tglong$to,tglong$from)
77 # expanded covariates
78 tglong <- expand.covs(tglong,c("x1","x2"))
79 # Cox model with different covariate
80 cx <- coxph(Surv(Tstart,Tstop,status)~x1.1+x2.2+strata(trans),
81 data=tglong,method="breslow")
82 summary(cx)
83 # new data, to check whether results are the same for transition 1 as
84 # those in appendix E.1 of Therneau & Grambsch (2000)
85 newdata <- data.frame(trans=1:3,x1.1=c(0,0,0),x2.2=c(0,1,0),strata=1:3)
86 HvH <- msfit(cx,newdata,trans=tmat)
87 # probtrans
88 pt <- probtrans(HvH,predt=0)
89 # predictions from state 1
90 pt[[1]]
91
92 }
93 \references{
94 Andersen PK, Borgan O, Gill RD, Keiding N (1993).
95 \emph{Statistical Models Based on Counting Processes}. Springer, New York.
96
97 Putter H, Fiocco M, Geskus RB (2007). Tutorial in biostatistics: Competing
98 risks and multi-state models. \emph{Statistics in Medicine} \bold{26},
99 2389--2430.
100
101 Therneau TM, Grambsch PM (2000). \emph{Modeling Survival Data: Extending the
102 Cox Model}. Springer, New York.
103
104 de Wreede LC, Fiocco M, and Putter H (2010). The mstate package for
105 estimation and prediction in non- and semi-parametric multi-state and
106 competing risks models. \emph{Computer Methods and Programs in Biomedicine}
107 \bold{99}, 261--274.
108
109 de Wreede LC, Fiocco M, and Putter H (2011). mstate: An R Package for the
110 Analysis of Competing Risks and Multi-State Models. \emph{Journal of
111 Statistical Software}, Volume 38, Issue 7.
112 }
113 \author{
114 Liesbeth de Wreede and Hein Putter \email{[email protected]}
115 }
116 \keyword{survival}