Extracting results from a function output

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20111017/8090f729/attachment.pl>
Assuming I'm reading your post correctly -- fit is the output object
and the lines following >fit are the console output, which implicitly
calls print -- it looks like the median isn't stored in fit but is
calculated on the fly in the print call. But this doesn't seem
consistent with your claim that:

"Print" function does not reveal them either.

Could you perhaps clarify your statement about print(fit)?

Cheers from Princeton!

Michael Weylandt
Hello,

I am having hard time obtaining a value from a function. "fit" is a survival
function that produces some results, such as "median", "confidence
intervals" etc. But str() function does not list these values. How can I
extract these to be able use them? For example, I need "median" value for
the group DrugA which is 48. "Print" function does not reveal them either.

Thank you.

fit
Call: survfit(formula = Surv(tT, dT) ~ gT, conf.type = "log-log")

records n.max n.start events median 0.95LCL 0.95UCL
gT=DrugA 9 9 9 6 48 32 NA
gT=DrugB 9 9 9 3 NA 42 NA
gT=DrugC 9 9 9 4 NA 42 NA
gT=Vehicle 9 9 9 8 40 37 45

str(fit)
List of 14
$ n : int [1:4] 9 9 9 9
$ time : num [1:28] 32 43 45 46 48 54 55 60 62 42 ...
$ n.risk : num [1:28] 9 8 7 6 5 4 3 2 1 9 ...
$ n.event : num [1:28] 1 1 1 1 1 0 1 0 0 2 ...
$ n.censor : num [1:28] 0 0 0 0 0 1 0 1 1 0 ...
$ surv : num [1:28] 0.889 0.778 0.667 0.556 0.444 ...
$ type : chr "right"
$ strata : Named int [1:4] 9 6 6 7
..- attr(*, "names")= chr [1:4] "gT=DrugA" "gT=DrugB" "gT=DrugC"
"gT=Vehicle"
$ std.err : num [1:28] 0.118 0.178 0.236 0.298 0.373 ...
$ upper : num [1:28] 0.984 0.939 0.878 0.805 0.719 ...
$ lower : num [1:28] 0.433 0.365 0.282 0.204 0.136 ...
$ conf.type: chr "log-log"
$ conf.int : num 0.95
$ call : language survfit(formula = Surv(tT, dT) ~ gT, conf.type =
"log-log")
- attr(*, "class")= chr "survfit"

Cem

Cem Girit, PhD

Biopticon Corporation

182 Nassau Street, Suite 204

Princeton, NJ 08542

Tel: (609)-853-0231

Email: ?<mailto:cgirit at biopticon.com> girit at biopticon.com

This email message and any attachments are confidential ...{{dropped:14}}

______________________________________________
R-help at r-project.org 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.

Often the summary() methods for the modelling functions
contain the kinds of details you are looking for.  Sometimes
there are special extractor functions but often not.
You have to study the help file for summary.<objectClass>
and the vignettes for the package, and perhaps do a little
experimentation to figure it out.

  > library(survival)
  > fit <- survfit(Surv(time, status) ~ x, data=leukemia)
  > fit
  Call: survfit(formula = Surv(time, status) ~ x, data = leukemia)

                  records n.max n.start events median 0.95LCL 0.95UCL
  x=Maintained         11    11      11      7     31      18      NA
  x=Nonmaintained      12    12      12     11     23       8      NA
  > summary(fit)$table[, "median"]
     x=Maintained x=Nonmaintained 
               31              23 
  > summary(fit)$table["x=Maintained", "median"]
  [1] 31

Bill Dunlap
Spotfire, TIBCO Software
wdunlap tibco.com
-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of R. Michael
Weylandt
Sent: Monday, October 17, 2011 8:51 AM
To: Cem Girit
Cc: r-help at r-project.org
Subject: Re: [R] Extracting results from a function output

Assuming I'm reading your post correctly -- fit is the output object
and the lines following >fit are the console output, which implicitly
calls print -- it looks like the median isn't stored in fit but is
calculated on the fly in the print call. But this doesn't seem
consistent with your claim that:

"Print" function does not reveal them either.

Could you perhaps clarify your statement about print(fit)?

Cheers from Princeton!

Michael Weylandt

On Mon, Oct 17, 2011 at 11:13 AM, Cem Girit <girit at biopticon.com> wrote:
Hello,

I am having hard time obtaining a value from a function. "fit" is a survival
function that produces some results, such as "median", "confidence
intervals" etc. But str() function does not list these values. How can I
extract these to be able use them? For example, I need "median" value for
the group DrugA which is 48. "Print" function does not reveal them either.

Thank you.

fit
Call: survfit(formula = Surv(tT, dT) ~ gT, conf.type = "log-log")

records n.max n.start events median 0.95LCL 0.95UCL
gT=DrugA 9 9 9 6 48 32 NA
gT=DrugB 9 9 9 3 NA 42 NA
gT=DrugC 9 9 9 4 NA 42 NA
gT=Vehicle 9 9 9 8 40 37 45

str(fit)
List of 14
$ n : int [1:4] 9 9 9 9
$ time : num [1:28] 32 43 45 46 48 54 55 60 62 42 ...
$ n.risk : num [1:28] 9 8 7 6 5 4 3 2 1 9 ...
$ n.event : num [1:28] 1 1 1 1 1 0 1 0 0 2 ...
$ n.censor : num [1:28] 0 0 0 0 0 1 0 1 1 0 ...
$ surv : num [1:28] 0.889 0.778 0.667 0.556 0.444 ...
$ type : chr "right"
$ strata : Named int [1:4] 9 6 6 7
..- attr(*, "names")= chr [1:4] "gT=DrugA" "gT=DrugB" "gT=DrugC"
"gT=Vehicle"
$ std.err : num [1:28] 0.118 0.178 0.236 0.298 0.373 ...
$ upper : num [1:28] 0.984 0.939 0.878 0.805 0.719 ...
$ lower : num [1:28] 0.433 0.365 0.282 0.204 0.136 ...
$ conf.type: chr "log-log"
$ conf.int : num 0.95
$ call : language survfit(formula = Surv(tT, dT) ~ gT, conf.type =
"log-log")
- attr(*, "class")= chr "survfit"

Cem

Cem Girit, PhD

Biopticon Corporation

182 Nassau Street, Suite 204

Princeton, NJ 08542

Tel: (609)-853-0231

Email: ?<mailto:cgirit at biopticon.com> girit at biopticon.com

This email message and any attachments are confidential ...{{dropped:14}}

______________________________________________
R-help at r-project.org 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.

Hello,

I am having hard time obtaining a value from a function. "fit" is a  
survival
function that produces some results, such as "median", "confidence
intervals" etc. But str() function does not list these values. How  
can I
extract these to be able use them? For example, I need "median"  
value for
the group DrugA which is 48. "Print" function does not reveal them  
either.
I'm not sure what you mean when you say the "Print" function does not  
"reveal them".  For one thing the function is spelled "print" and for  
another thing I see the desired "48" in the output.

http://tolstoy.newcastle.edu.au/R/e6/help/09/05/15413.html

So the answer in your case is:

summary(fit)$table[1, ]
David.

>
> Thank you.
>
>> fit
> Call: survfit(formula = Surv(tT, dT) ~ gT, conf.type = "log-log")
>
> records n.max n.start events median 0.95LCL 0.95UCL
> gT=DrugA 9 9 9 6 48 32 NA
> gT=DrugB 9 9 9 3 NA 42 NA
> gT=DrugC 9 9 9 4 NA 42 NA
> gT=Vehicle 9 9 9 8 40 37 45
>
>> str(fit)
> List of 14
> $ n : int [1:4] 9 9 9 9
> $ time : num [1:28] 32 43 45 46 48 54 55 60 62 42 ...
> $ n.risk : num [1:28] 9 8 7 6 5 4 3 2 1 9 ...
> $ n.event : num [1:28] 1 1 1 1 1 0 1 0 0 2 ...
> $ n.censor : num [1:28] 0 0 0 0 0 1 0 1 1 0 ...
> $ surv : num [1:28] 0.889 0.778 0.667 0.556 0.444 ...
> $ type : chr "right"
> $ strata : Named int [1:4] 9 6 6 7
> ..- attr(*, "names")= chr [1:4] "gT=DrugA" "gT=DrugB" "gT=DrugC"
> "gT=Vehicle"
> $ std.err : num [1:28] 0.118 0.178 0.236 0.298 0.373 ...
> $ upper : num [1:28] 0.984 0.939 0.878 0.805 0.719 ...
> $ lower : num [1:28] 0.433 0.365 0.282 0.204 0.136 ...
> $ conf.type: chr "log-log"
> $ conf.int : num 0.95
> $ call : language survfit(formula = Surv(tT, dT) ~ gT, conf.type =
> "log-log")
> - attr(*, "class")= chr "survfit"
>
>
>
> Cem
>
>
>
> Cem Girit, PhD
>
>
>
> Biopticon Corporation
>
> 182 Nassau Street, Suite 204
>
> Princeton, NJ 08542
>
> Tel: (609)-853-0231
>
> Email:  <mailto:cgirit at biopticon.com> girit at biopticon.com
>
>
>
> This email message and any attachments are confidential ...{{dropped: 
> 14}}
>
> ______________________________________________
> R-help at r-project.org 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.

David Winsemius, MD
West Hartford, CT