Dear Steven,
> -----Original Message-----
> From: Steven Yen [mailto:sye...@gmail.com]
> Sent: June 29, 2016 9:39 AM
> To: Fox, John <j...@mcmaster.ca>
> Cc: R-help <r-help@r-project.org>; Sandy Weisberg (sa...@umn.edu)
> <sa...@umn.edu>
> Subject: Re: [R] t-test for regression estimate
>
> Thanks John. Yes, by using verbose=T, I get the value of the hypothesis. But
> tell
> me again, how would I get the variance (standard error)?
Using verbose=TRUE *prints* the value of the hypothesis but doesn't save it in
the returned object, making it inconvenient to compute on it. As well, when
verbose is TRUE we should probably also print the covariance matrix for the
hypothesis, which we don't do at present, but which I'll add when I have a
chance.
From ?linearHypothesis in the development version of car: "The value of the
linear hypothesis and its covariance matrix are returned respectively as
"value" and "vcov" attributes of the object (but not printed)." Thus, for
example,
---------------- snip ------------
> library(car)
> mod <- lm(prestige ~ income + education, data=Duncan)
> lh <- linearHypothesis(mod, "income = education"))
> attr(lh, "value")
[,1]
income = education 0.05289891
> attr(lh, "vcov")
income = education
income = education 0.04101096
---------------- snip ------------
The reason that l used attributes is that linearHypothesis() returns an "anova"
object, which is printed by print.anova(). Adding components directly to that
object would disturb printing it. I could introduce a new class of objects but,
though that would be more intuitive, and though I may end up doing that, it is
probably unwarranted given the rarity of wanting to access the value and
covariance matrix of the hypothesis.
Best,
John
>
>
> On 6/29/2016 11:56 AM, Fox, John wrote:
>
>
> Dear Steven,
>
> OK -- that makes sense, and there was also a previous request for
> linearHypothesis() to return the value of the hypothesis and its covariance
> matrix. In your case, where there's only 1 numerator df, that would be the
> value and estimated sampling variance of the hypothesis.
>
> I've now implemented that, using (at least provisionally) attributes in
> the development version of the car package on R-Forge, which you should be
> able to install via install.packages("car",
> repos="http://R-Forge.R-project.org";
> <http://R-Forge.R-project.org> ). Then see ?linearHypothesis for more
> information.
>
> Best,
> John
>
>
> -----Original Message-----
> From: Steven Yen [mailto:sye...@gmail.com]
> Sent: June 28, 2016 3:44 PM
> To: Fox, John <j...@mcmaster.ca>
> <mailto:j...@mcmaster.ca>
> Cc: R-help <r-help@r-project.org> <mailto:r-help@r-
> project.org>
> Subject: Re: [R] t-test for regression estimate
>
> Thanks John. Reason is I am doing linear transformations of
> many coefficients
> (e.g., bi / scalar). Of course I can uncover the t-statistic
> from
> the F statistic and
> then the standard error. Simply scaling the estimated
> coefficients I can also
> transform the standard errors. I have since found deltaMethod
> from library
> "car" useful. Its just that, if linearHypothesis had provide the
> standard errors
> and t-statistics then the operation would have been easier,
> with a one-line
> command for each coefficient. Thank you again.
>
>
> On 6/28/2016 6:28 PM, Fox, John wrote:
>
>
> Dear Steven,
>
> The reason that linearHypothesis() computes a Wald F
> or chisquare
> test rather than a t or z test is that the (numerator) df for
> the
> linear hypothesis
> need not be 1.
>
> In your case (as has been pointed out) you can get the
> coefficient
> standard error directly from the model summary.
>
> More generally, with some work, you could solve for
> the the SE for a 1
> df linear hypothesis in terms of the value of the linear
> function
> of coefficients
> and the F or chisquare. That said, I'm not sure why you want to
> do this.
>
> I hope this helps,
> John
>
> -----------------------------
> John Fox, Professor
> McMaster University
> Hamilton, Ontario
> Canada L8S 4M4
> Web: socserv.mcmaster.ca/jfox
>
>
>
> -----Original Message-----
> From: R-help [mailto:r-help-bounces@r-
> project.org] On Behalf
> Of Steven Yen
> Sent: June 28, 2016 9:27 AM
> To: R-help <r-help@r-project.org> <mailto:r-
> h...@r-project.org> <mailto:r-help@r-
> project.org> <mailto:r-help@r-project.org>
> Subject: [R] t-test for regression estimate
>
> test option for linearHypothesis in library(car)
> include "Chisq"
> and "F". I prefer
> a simple t-test so that I can retrieve the
> standard error.
> Any options other than linearHypothesis to
> test the linear
> hypothesis (with 1
> restriction/degree of freedom)?
>
> > summary(ols1)
>
> Coefficients:
> Estimate Std. Error t value
> Pr(>|t|)
> (Intercept) -0.20013 0.09199 -2.176 0.0298
> *
> age 0.04054 0.01721 2.355
> 0.0187 *
> suburb 0.01911 0.05838 0.327 0.7435
> smcity -0.29969 0.19175 -1.563 0.1184
> ---
> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’
> 0.05 ‘.’
> 0.1 ‘ ’ 1
>
> > linearHypothesis(ols1,"suburb")
> Linear hypothesis test
>
> Hypothesis:
> suburb = 0
>
> Model 1: restricted model
> Model 2: polideo ~ age + suburb + smcity
>
> Res.Df RSS Df Sum of Sq F Pr(>F)
> 1 888 650.10
> 2 887 650.02 1 0.078534 0.1072 0.7435
>
>
> [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help@r-project.org <mailto:R-help@r-
> project.org> <mailto:R-help@r-project.org> <mailto:R-help@r-project.org>
> mailing
> list -- To UNSUBSCRIBE and more, see
> 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@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
