Hi, If I have: foo <- survfit(y ~ x) where y is a survival object and x is a n-level factor. The documentation says when I plot(foo), the confidence intervals will not be plotted (which I guess is understandable as otherwise the plot will get really messy). I tried to plot with confidence intervals by using: plot(foo, conf.int = TRUE) and indeed the resulting plot is messy. However I'm just wondering if I can (suppose x is a 2-level factor) use different colours and line types for the confidence lines? If I do: plot(foo, conf.int = TRUE, col = 1:2) then I'll get two different colours. What I would like is to then plot the confidence lines using lty = 2 (while keeping the colour). Can I do this? -- Cheers, Kevin ------------------------------------------------------------------------------ /* Time is the greatest teacher, unfortunately it kills its students */ -- Ko-Kang Kevin Wang Master of Science (MSc) Student SLC Tutor and Lab Demonstrator Department of Statistics University of Auckland New Zealand Homepage: http://www.stat.auckland.ac.nz/~kwan022 Ph: 373-7599 x88475 (City) x88480 (Tamaki)
You could try something like: plot(foo[1],conf.int=TRUE) par(new=TRUE) plot(foo[2],conf.int=TRUE,col=2) Seems to work! David ----- Original Message ----- From: "Ko-Kang Kevin Wang" <kwan022 at stat.auckland.ac.nz> To: "R Help" <r-help at stat.math.ethz.ch> Sent: Wednesday, March 26, 2003 12:13 PM Subject: [R] Plotting K-M Curve when have several strata> Hi, > > If I have: > foo <- survfit(y ~ x) > where y is a survival object and x is a n-level factor. The documentation > says when I plot(foo), the confidence intervals will not be plotted (which > I guess is understandable as otherwise the plot will get really messy). > > I tried to plot with confidence intervals by using: > plot(foo, conf.int = TRUE) > and indeed the resulting plot is messy. However I'm just wondering if I > can (suppose x is a 2-level factor) use different colours and line types > for the confidence lines? If I do: > plot(foo, conf.int = TRUE, col = 1:2) > then I'll get two different colours. What I would like is to then plot > the confidence lines using lty = 2 (while keeping the colour). > > Can I do this? > > -- > Cheers, > > Kevin > > ------------------------------------------------------------------------------> /* Time is the greatest teacher, unfortunately it kills its students */ > > -- > Ko-Kang Kevin Wang > Master of Science (MSc) Student > SLC Tutor and Lab Demonstrator > Department of Statistics > University of Auckland > New Zealand > Homepage: http://www.stat.auckland.ac.nz/~kwan022 > Ph: 373-7599 > x88475 (City) > x88480 (Tamaki) > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-help > >
Kevin, If you really want to get control of the colours then pick up the relevant returned values and pass them individually to lines(). foo[[2]] will hold time axis, foo[[8]] and [[9]]the upper and lower ci. I actually feed the ci values into polygon() and am then able to produce shaded confidence intervals. eg fit.r <- survfit(Surv(fuperiod, censor), data=s.data, type= "kaplan-meier", conf.type="plain", conf.lower="peto") x <- c(0,fit.r[[2]]) #add at time 0 y <- c(1,fit.r[[5]]) plot(x,y, col="blue",type="n",xlab="Time (years)",ylab="Proportion surviving") xp <- c(x,rev(x)) yp <- c(1,fit.r[[8]],rev(fit.r[[9]]),1) polygon(xp,yp,density=NULL,col="pink", border= "pink", lwd=0.5) lines(x,y, col="blue",type="l",lwd=3) Paul On Wednesday, March 26, 2003, at 12:13 pm, Ko-Kang Kevin Wang wrote:> Hi, > > If I have: > foo <- survfit(y ~ x) > where y is a survival object and x is a n-level factor. The > documentation > says when I plot(foo), the confidence intervals will not be plotted > (which > I guess is understandable as otherwise the plot will get really messy). > > I tried to plot with confidence intervals by using: > plot(foo, conf.int = TRUE) > and indeed the resulting plot is messy. However I''m just wondering if > I > can (suppose x is a 2-level factor) use different colours and line > types > for the confidence lines? If I do: > plot(foo, conf.int = TRUE, col = 1:2) > then I''ll get two different colours. What I would like is to then plot > the confidence lines using lty = 2 (while keeping the colour). > > Can I do this? > > -- > Cheers, > > Kevin > > ----------------------------------------------------------------------- > ------- > /* Time is the greatest teacher, unfortunately it kills its students */ > > -- > Ko-Kang Kevin Wang > Master of Science (MSc) Student > SLC Tutor and Lab Demonstrator > Department of Statistics > University of Auckland > New Zealand > Homepage: http://www.stat.auckland.ac.nz/~kwan022 > Ph: 373-7599 > x88475 (City) > x88480 (Tamaki) > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-help > >Prof. P. B. Pynsent, Research and Teaching Centre, Royal Orthopaedic Hospital, Birmingham, B31 2AP, U.K.