[R] Left-truncated regression
Tom La Bone
booboo at gforcecable.com
Tue Dec 2 19:48:30 CET 2008
Look at the sand package, which is available at
http://www.csm.ornl.gov/esh/statoed/
and the NADA package, which is available from CRAN. One or both may have
items of interest.
Tom
Zita wrote:
>
> Hi.
>
> I am looking for a function for left-truncated data.
> I have one data set with 2 variables (Hours~Yrs_Ed).
> I already left-censored the data at 200 and left-truncated it at the same
> spot, so that I am able to make 2 estimations (one for censoring and one
> for truncation).
> I know how to make the linear regression for the left-censored variable
> (hours) and how to plot the regression line into the (x,y) plot (packages
> AER, Zeileis, Survival, ...):
>
> tfit<-survreg(Surv(Hours,Hours>0,
> type='left')~Yrs_Ed,data=DataWomen,dist='gaussian')
> z<-predict(tfit,type="response")
> plot(Yrs_Ed,Hours)
> abline(tfit)
>
> My aim is to compare the effects of truncation and censoring graphically
> by plotting the two regression lines into one plot with both datasets
> (censored and truncated).
> I just can't figure out how to write the function for left-truncated data
> and what package to use for this. I only need "left-truncation", not
> "left-truncation and right-censoring".
> I hope somebody can help me with that matter.
>
> Zita
>
>
>
--
View this message in context: http://www.nabble.com/Left-truncated-regression-tp20789446p20798448.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help
mailing list