R help - Jan 2014 - A question in rms package

Dear all, 

Happy new year all of You and with best wishes coming to you in this new year.

I have a problem in running a command in rms package.
Does any can help me with my problem.

I wanna use predab.resample command to compute bias-corrected estimates of a
vector of indexes of Predictive accuracy. But I'm confused about choosing
fit and measure arguments.

Would you please help me? 

I ran this command:
model1=lrm(Cancerous~AGE+PV+PSA,na.action=na.delete,x=TRUE, y=TRUE, data=mdat1)

now when I want to use this one:

predab.resample<-predab.resample(model,
method=c("boot","crossvalidation",".632","randomization"),
bw=TRUE, B=50, pr=FALSE,
rule="aic", type="residual", sls=.05, aics=0,
tol=1e-12, non.slopes.in.x=TRUE)


I received this error:

Error in predab.resample(model, method = c("boot",
"crossvalidation",  :
  argument "fit" is missing, with no default


I will be very happy to receive your comments.

Many thanks
Amir

	[[alternative HTML version deleted]]

On Jan 2, 2014, at 11:03 AM, Agony wrote:
> Dear all, 
> 
> Happy new year all of You and with best wishes coming to you in this new
year.
> 
> I have a problem in running a command in rms package.
> Does any can help me with my problem.
> 
> I wanna use predab.resample command to compute bias-corrected estimates of
a vector of indexes of Predictive accuracy. But I'm confused about choosing
fit and measure arguments.
> 
> Would you please help me? 
> 
> I ran this command:
> model1=lrm(Cancerous~AGE+PV+PSA,na.action=na.delete,x=TRUE, y=TRUE,
data=mdat1)
___^
> 
> now when I want to use this one:
> 
> predab.resample<-predab.resample(model,
method=c("boot","crossvalidation",".632","randomization"),
_____________________________________^

Not spelled the same.

> bw=TRUE, B=50, pr=FALSE,
> rule="aic", type="residual", sls=.05, aics=0,
> tol=1e-12, non.slopes.in.x=TRUE)
> 
> 
> I received this error:
> 
> Error in predab.resample(model, method = c("boot",
"crossvalidation",  :
>   argument "fit" is missing, with no default
> 
-- 
David Winsemius
Alameda, CA, USA