If you really want your coefficient estimates to be scale-equivariant you
should test those methods for such a thing. E.g., here are functions that
let you check how scaling one predictor affects the estimated coefficients
- they should give the same results for any scale factor.
f <-
function (s
I found a fix to my problem using the fastLm() from package RcppEigen, using
the Jacobi singular value decomposition (SVD) (method 4) or a method based
on the eigenvalue-eigenvector decomposition of X'X - method 5 of the fastLm
function
install.packages("RcppEigen")
library(RcppEigen)
n_obs <-
s Applications,
Australian National University, Canberra ACT 0200.
On 29/03/2015, at 23:00,
mailto:r-help-requ...@r-project.org>>
mailto:r-help-requ...@r-project.org>> wrote:
From: Ben Bolker mailto:bbol...@gmail.com>>
Subject: Re: [R] Error in lm() with very small (close t
RiGui business.uzh.ch> writes:
>
[snip]
> I am terribly sorry for the code not being reproducible, is the
> first time I am posting here, I run the code several times before I
> posted, but...I forgot about the library used.
Thanks for updating.
> To answer to your questions:
>
>> How d
RiGui business.uzh.ch> writes:
>
[snip]
> I am terribly sorry for the code not being reproducible, is the
> first time I am posting here, I run the code several times before I
> posted, but...I forgot about the library used.
Thanks for updating.
> To answer to your questions:
>
>> How do
> On 28 Mar 2015, at 18:52 , RiGui wrote:
>
> Thank you for your replies!
>
> I am terribly sorry for the code not being reproducible, is the first time I
> am posting here, I run the code several times before I posted, but...I
> forgot about the library used.
>
> To answer to your questions:
Thank you for your replies!
I am terribly sorry for the code not being reproducible, is the first time I
am posting here, I run the code several times before I posted, but...I
forgot about the library used.
To answer to your questions:
How do you know this answer is "correct"?
What I am doing
> On 28 Mar 2015, at 18:28 , Ben Bolker wrote:
>
> peter dalgaard gmail.com> writes:
>
>>
>>
>>> On 28 Mar 2015, at 00:32 , RiGui business.uzh.ch> wrote:
>>>
>>> Hello everybody,
>>>
>>> I have encountered the following problem with lm():
>>>
>>> When running lm() with a regressor close
peter dalgaard gmail.com> writes:
>
>
> > On 28 Mar 2015, at 00:32 , RiGui business.uzh.ch> wrote:
> >
> > Hello everybody,
> >
> > I have encountered the following problem with lm():
> >
> > When running lm() with a regressor close to zero -
> of the order e-10, the
> > value of the estim
> On 28 Mar 2015, at 00:32 , RiGui wrote:
>
> Hello everybody,
>
> I have encountered the following problem with lm():
>
> When running lm() with a regressor close to zero - of the order e-10, the
> value of the estimate is of huge absolute value , of order millions.
>
> However, if I write
Hello everybody,
I have encountered the following problem with lm():
When running lm() with a regressor close to zero - of the order e-10, the
value of the estimate is of huge absolute value , of order millions.
However, if I write the formula of the OLS estimator, in matrix notation:
pseudoinv
11 matches
Mail list logo
