R help - Jun 2007 - How to obtain coefficient standard error from the result of polr?

Hi - I am using polr. I can get a result from polr fit by calling

result.plr <- polr(formula, data=mydata, method="probit");

However, from the 'result.plr', how can I access standard error of the
estimated coefficients as well as the t statistics for each one of them?

What I would like to do ultimately is to see which coefficients are not
significant and try to refit the model again by excluding those variables out. I
would appreciate if anyone could give some hint on this. Thank you.

- adschai

	[[alternative HTML version deleted]]

On Mon, 4 Jun 2007, adschai at optonline.net wrote:
> Hi - I am using polr. I can get a result from polr fit by calling
>
> result.plr <- polr(formula, data=mydata, method="probit");
>
> However, from the 'result.plr', how can I access standard error of
the
> estimated coefficients as well as the t statistics for each one of them?
You do this from summary(result.plr), possibly via 
coef(summary(result.plr))
> What I would like to do ultimately is to see which coefficients are not 
> significant and try to refit the model again by excluding those 
> variables out. I would appreciate if anyone could give some hint on 
> this. Thank you.
There is a multiple comparisons problem in doing that, especially so if 
the coefficients refer to multi-level factors.  Using stepAIC is 
better-supported.
> - adschai
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
>
-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

You need to call the summary() method to obtain the standard errors, 
e.g.,

result.plr <- polr(formula, data = mydata, method = "probit", Hess
=
TRUE)
coef(summary(result.plr))

for checking which predictors are significant you also use stepAIC() 
or the bootstrap version of it, i.e., boot.stepAIC() in the 
`bootStepAIC' package, e.g.,

library(bootStepAIC)
boot.stepAIC(result.plr, data = mydata)


I hope it helps.

Best,
Dimitris

----
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven

Address: Kapucijnenvoer 35, Leuven, Belgium
Tel: +32/(0)16/336899
Fax: +32/(0)16/337015
Web: http://med.kuleuven.be/biostat/
     http://www.student.kuleuven.be/~m0390867/dimitris.htm


----- Original Message ----- 
From: <adschai at optonline.net>
To: <r-help at stat.math.ethz.ch>
Sent: Monday, June 04, 2007 8:02 AM
Subject: [R] How to obtain coefficient standard error from the result 
ofpolr?

> Hi - I am using polr. I can get a result from polr fit by calling
>
> result.plr <- polr(formula, data=mydata, method="probit");
>
> However, from the 'result.plr', how can I access standard error of 
> the estimated coefficients as well as the t statistics for each one 
> of them?
>
> What I would like to do ultimately is to see which coefficients are 
> not significant and try to refit the model again by excluding those 
> variables out. I would appreciate if anyone could give some hint on 
> this. Thank you.
>
> - adschai
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
> 

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm