[R] (coxph, se) Obtaining standard errors of coefficients from coxph to store

2007-08-16 Thread David Lloyd 
Hi all,

I'm wanting to be able to find and store the z-score of coxph below: -

modz=coxph(Surv(TSURV,STATUS)~RAGE+DAGE+REG_WTIME_M+CLD_ISCH+POLY_VS,
data=kidneyT,method="breslow")


I know summary(modz) will give me this, but how do i extract the
standard error or z-score values in a similar way to obtaining the
coefficients by coef(modz) ? I think it must be something to do with
modz$var but I'm having a complete mental blank.

I need this info so I can write a function to use within a bootstrap so
I can record the number of times (proportion) each variable in the Cox
PH model is actually significant over all the bootstrap resamples.

Any assistance is greatly appreciated

DL 


Click to find local singles for dating, romance and fun.
 



___Get
 the Free email that has everyone talking at http://www.mail2world.com 
target=new>http://www.mail2world.com  Unlimited 
Email Storage – POP3 – Calendar – SMS – Translator – 
Much More!
[[alternative HTML version deleted]]

__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

Re: [R] (coxph, se) Obtaining standard errors of coefficients from coxph to store

2007-08-27 Thread joris . dewolf 


David,

It would be helpful to give an example of what you would like to extract.

I guess you know how to extract elements from vectors and lists.
However, sometimes the objects returned by functions can be rather complex
(output of coxph() is...)
A general method to capture printed output is via capture.output(). Maybe
not fast, but if you have no other solution...

Joris

> a <- rnorm(10,1,1)
> b <- rnorm(10,1,1)
> mod <- lm(a~b)
> smod <- summary(mod)
> smod

Call:
lm(formula = a ~ b)

Residuals:
Min  1Q  Median  3Q Max
-1.7482 -0.5991  0.1211  0.8341  1.4975

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept)   1.6210 0.5332   3.040   0.0161 *
b-0.7667 0.5037  -1.522   0.1664
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 1.142 on 8 degrees of freedom
Multiple R-Squared: 0.2246, Adjusted R-squared: 0.1277
F-statistic: 2.317 on 1 and 8 DF,  p-value: 0.1664

> output <- capture.output(print(smod))
> output
 [1] ""
 [2] "Call:"
 [3] "lm(formula = a ~ b)"
 [4] ""
 [5] "Residuals:"
 [6] "Min  1Q  Median  3Q Max "
 [7] "-1.7482 -0.5991  0.1211  0.8341  1.4975 "
 [8] ""
 [9] "Coefficients:"
[10] "Estimate Std. Error t value Pr(>|t|)  "
[11] "(Intercept)   1.6210 0.5332   3.040   0.0161 *"
[12] "b-0.7667 0.5037  -1.522   0.1664  "
[13] "---"
[14] "Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 "
[15] ""
[16] "Residual standard error: 1.142 on 8 degrees of freedom"
[17] "Multiple R-Squared: 0.2246,\tAdjusted R-squared: 0.1277 "
[18] "F-statistic: 2.317 on 1 and 8 DF,  p-value: 0.1664 "
[19] ""





   
 "David Lloyd" 
 <[EMAIL PROTECTED] 
 lloyd.com> To 
 Sent by:
 [EMAIL PROTECTED]  cc 
 at.math.ethz.ch   
   Subject 
   [R] (coxph,  se) Obtaining standard 
 16/08/2007 11:31  errors of coefficients from coxph   
   to store
   
   
   
   
   
   




Hi all,

I'm wanting to be able to find and store the z-score of coxph below: -

modz=coxph(Surv(TSURV,STATUS)~RAGE+DAGE+REG_WTIME_M+CLD_ISCH+POLY_VS,
data=kidneyT,method="breslow")


I know summary(modz) will give me this, but how do i extract the
standard error or z-score values in a similar way to obtaining the
coefficients by coef(modz) ? I think it must be something to do with
modz$var but I'm having a complete mental blank.

I need this info so I can write a function to use within a bootstrap so
I can record the number of times (proportion) each variable in the Cox
PH model is actually significant over all the bootstrap resamples.

Any assistance is greatly appreciated

DL


Click to find local singles for dating, romance and fun.




___Get
the Free email that has everyone talking at http://www.mail2world.com target=new>http://www.mail2world.com
Unlimited Email Storage – POP3 – Calendar
– SMS – Translator – Much More!
 [[alternative HTML version deleted]]

__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.

__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.