multiple time-dependent covariates in cox regression

classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|

multiple time-dependent covariates in cox regression

gherma1
This post has NOT been accepted by the mailing list yet.
I would like to enter multiple time-dependent covariates in a cox regression model.
Any suggestions on how to label the different time-dependent covariates because I receive errors with T_COV_A and T_COV_B?
Thanks

TIME PROGRAM.
COMPUTE T_COV_A = T_ *A T_COV_B = T_ *B
COXREG   csurvival
  /STATUS=Status(1)
  /CONTRAST (A)=Indicator
  /CONTRAST (B)=Indicator(1)
  /METHOD=ENTER A B T_COV_A T_CO_B
  /PRINT=CI(95)
  /CRITERIA=PIN(.05) POUT(.10) ITERATE(20).

>Error # 4285 in column 19.  Text: T_
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
Reply | Threaded
Open this post in threaded view
|

Re: multiple time-dependent covariates in cox regression

Bruce Weaver
Administrator
I don't have time to go generate and test an example right now, but the first thing that caught my eye was the missing command terminator on your COMPUTE line, and the fact that you attempt to compute two variables with a single COMPUTE command.  I.e., I wondered if this might work better:

TIME PROGRAM.
COMPUTE T_COV_A = T_ *A.
COMPUTE T_COV_B = T_ *B.

COXREG   csurvival
  /STATUS=Status(1)
  /CONTRAST (A)=Indicator
  /CONTRAST (B)=Indicator(1)
  /METHOD=ENTER A B T_COV_A T_CO_B
  /PRINT=CI(95)
  /CRITERIA=PIN(.05) POUT(.10) ITERATE(20).

HTH.

gherma1 wrote
I would like to enter multiple time-dependent covariates in a cox regression model.
Any suggestions on how to label the different time-dependent covariates because I receive errors with T_COV_A and T_COV_B?
Thanks

TIME PROGRAM.
COMPUTE T_COV_A = T_ *A T_COV_B = T_ *B
COXREG   csurvival
  /STATUS=Status(1)
  /CONTRAST (A)=Indicator
  /CONTRAST (B)=Indicator(1)
  /METHOD=ENTER A B T_COV_A T_CO_B
  /PRINT=CI(95)
  /CRITERIA=PIN(.05) POUT(.10) ITERATE(20).

>Error # 4285 in column 19.  Text: T_
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: multiple time-dependent covariates in cox regression

Bruce Weaver
Administrator
It just occurred to me that people not using NABBLE might get the BOLD codes coming through as asterisks.  So here are those two COMPUTE commands again without any BOLD codes:

COMPUTE T_COV_A = T_ *A.
COMPUTE T_COV_B = T_ *B.


Bruce Weaver wrote
I don't have time to go generate and test an example right now, but the first thing that caught my eye was the missing command terminator on your COMPUTE line, and the fact that you attempt to compute two variables with a single COMPUTE command.  I.e., I wondered if this might work better:

TIME PROGRAM.
COMPUTE T_COV_A = T_ *A.
COMPUTE T_COV_B = T_ *B.

COXREG   csurvival
  /STATUS=Status(1)
  /CONTRAST (A)=Indicator
  /CONTRAST (B)=Indicator(1)
  /METHOD=ENTER A B T_COV_A T_CO_B
  /PRINT=CI(95)
  /CRITERIA=PIN(.05) POUT(.10) ITERATE(20).

HTH.

gherma1 wrote
I would like to enter multiple time-dependent covariates in a cox regression model.
Any suggestions on how to label the different time-dependent covariates because I receive errors with T_COV_A and T_COV_B?
Thanks

TIME PROGRAM.
COMPUTE T_COV_A = T_ *A T_COV_B = T_ *B
COXREG   csurvival
  /STATUS=Status(1)
  /CONTRAST (A)=Indicator
  /CONTRAST (B)=Indicator(1)
  /METHOD=ENTER A B T_COV_A T_CO_B
  /PRINT=CI(95)
  /CRITERIA=PIN(.05) POUT(.10) ITERATE(20).

>Error # 4285 in column 19.  Text: T_
>Incorrect variable name: either the name is more than 64 characters, or it is
>not defined by a previous command.
>Execution of this command stops.
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.
Reply | Threaded
Open this post in threaded view
|

Re: multiple time-dependent covariates in cox regression

gherma1
This post has NOT been accepted by the mailing list yet.
In reply to this post by gherma1
Thank you very much for your reply

It worked with:
COMPUTE T_COV1_ = T_ * A.
COMPUTE T_COV2_ = T_ * B.
Reply | Threaded
Open this post in threaded view
|

Re: multiple time-dependent covariates in cox regression

Art Kendall
In reply to this post by gherma1
COMPUTE T_COV_A = T_ *A T_COV_B = T_ *B
Haven't used this command. However looking at the syntax documentation, it may be that the transformationS must follow the usual syntax for COMPUTE.
See whether multiple COMPUTEs work for you.
Art Kendall
Social Research Consultants
Reply | Threaded
Open this post in threaded view
|

Re: multiple time-dependent covariates in cox regression

Bruce Weaver
Administrator
In reply to this post by gherma1
Nabble is saying that the OP's posts have not been delivered to the mailing list.  I Nabble is telling the truth about that, some of you will have missed the response quoted below.

gherma1 wrote
Thank you very much for your reply

It worked with:
COMPUTE T_COV1_ = T_ * A.
COMPUTE T_COV2_ = T_ * B.
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.