Hello,
I am using the locfit to fit a non parametric glm model to data with a gamma
distributed response variable. In the parametric glm regression the diagnostics
were based on the study of the standardized deviance or pearson residuals. How
can I estimate the the standardized Pearson residua
Hello! I am having a problem understanding what the weights option in
the locfit command of the locfit package is doing. I
have written a sample program which illustrates the issue (below). The
example involves using bootstrap however, that is not my main
goal but it illustrates where my problem li
I got a request from a reputable source (who nonetheless did not copy
the list, a fact that I only noticed after responding) to post a full
worked example:
I just tested the bits that I had earlier posted and they seem to fit
together. The OP was asking for some sort of density conditional
On Jul 6, 2010, at 7:08 AM, Arnab Maity wrote:
Hi,
Can you provide me an example in R to estimate the density using
locfit package with the help of multi dimensional explanatory
variables and one dimensional dependent variable?
When I came up with a solution I posted it:
https://stat.et
Hi,
Can you provide me an example in R to estimate the density using locfit package
with the help of multi dimensional explanatory variables and one dimensional
dependent variable?
Thank you.
Arnab Kumar Maity
Research Assistant
Indian School of Business
Hyderabad, India
DISCLAIMER:\ This e-ma
elihood has been MIA
> for a few years, so I can't check there. In any case it doesn't seem
> like the number of data points and/or computing power are bigger issue.
>
> Andy
>
>> -Original Message-
>> From: r-help-boun...@r-project.org
>> [ma
Hi All,
In another thread Andy Liaw, who CRAN lists as locfit maintainer; said:
From: "Liaw, Andy"
To: "Guy Green" ;
Subject: Re: Alternatives to linear regression with multiple variables
Date: 22 February 2010 17:50
You can try the locfit package, which I believe can handle up to 5
variables.
Just replacing preplot() with predict() should be fine.
BTW, it's always a good idea to specify the version of the package
you're using as well.
Best,
Andy
From: mh...@berkeley.edu
>
> Hi,
>
> I'm trying to work through the examples and code in Loader's
> LOCAL REGRESSION AND LIKELIHOOD, and
Hi,
I'm trying to work through the examples and code in Loader's
LOCAL REGRESSION AND LIKELIHOOD, and have run into a problem
with the code for one sided smoothing and change point analysis
(p. 110-112).
The code, after loading locfit:
midp<-(1945:1988)+0.5
fitl<-locfit(thickness~left(year), dat
On Tue, 03 Mar 2009 22:10:42 +0100, David Winsemius
wrote:
That is what I thought to be the critical paragraph. The variance is
assumed to be = 1 when you use family="gaussian" rather than the default
of family="qgauss". You give it a vector, 1000*rnorm(100), that ranges
widely and a sma
That is what I thought to be the critical paragraph. The variance is
assumed to be = 1 when you use family="gaussian" rather than the
default of family="qgauss". You give it a vector, 1000*rnorm(100),
that ranges widely and a small (relative) variance is assumed and so
the confidence interv
David Winsemis wrote:
I think you should read (or re-read) the locfit help page and *also*
the links from that page to the help pages for locfit.raw and rv. I
would have thought that since family= is not an argument to locfit per
se, but rather is documented in locfit.raw that you have ye
From: Suresh Krishna
[...]
> ps. The package maintainer, Catherine Loader, is no longer
> reachable at
> her Auckland address.
For the record, I'm the package maintainer for locfit, and I have not
exactly vanished (yet). Please see the package description.
That said, it doesn't mean I know a
I think you should read (or re-read) the locfit help page and *also*
the links from that page to the help pages for locfit.raw and rv. I
would have thought that since family= is not an argument to locfit per
se, but rather is documented in locfit.raw that you have yet done so,
but perhaps
Dear all,
I just realized that using family="qgauss" restores normal-looking
confidence bands... I read that using family="gaussian" rather than
family="qgauss" fixes the dispersion parameter at 1, but without knowing
the theory behind the code, I dont understand why there is such a
diff
Dear list members,
I am trying to understand this output from the smoothing package locfit
(1.5-4, running on R 2.8.1 on Windows Vista 64 bit).
# sample code
x<-1:100
y<-rnorm(100)
fit<-locfit(y~x,family="gaussian") #default parameters are fine
plot(fit,band="global") #plot seems "reasona
My guess is that you have not configured you new installation to see
(and update) your collection of packages. As a quick fix, what happens
when you go to your favorite CRAN mirror and install a new copy of
locfit? My version is 1.5-4 and runs with recent versions of R.
--
David Winsemius,
I have been using some old R scripts that were prepared for me using
R Version 1.9.0. In these, there is a call to
library(locfit)
and with this version of R, I have no problem.
But needing to upgrade to the latest version of R, I find these
scripts no longer work, and with
help(locfit)
I ge
Hello all!
I have recently started using the LOCFIT package, together with Clive
Loader's book. I need to implement some method for automatic (plug-in)
bandwidth selection in a multivariate kernel regression. From the book, and
the LOCFIT documentation, it is not clear whether this is possible.
19 matches
Mail list logo
