> You can use the "offset" function as part of a formula in "lm" (and
> other model fitting functions) to set a specific slope or set of
> slopes. Using this up front will give you the correct residuals,
> standard errors, etc. This is better than trying to modify a fitted
> regression object.
G
> Even if this is possible, won't all the other estimates (i.e., standard error
> of betas) produced be junk since they aren't derived from the associated
> estimators?
That was actually my primary concern. It looks like the offset is the
solution.
Thanks.
Collin.
>
> Michael
>
You can use the "offset" function as part of a formula in "lm" (and
other model fitting functions) to set a specific slope or set of
slopes. Using this up front will give you the correct residuals,
standard errors, etc. This is better than trying to modify a fitted
regression object.
On Tue, Nov
On Nov 12, 2013, at 11:59, wrote:
>> Think you're going to have to explicitly define "hand tailor." I
>> haven't a clue what you mean. (Someone else might of course).
>
> Ah, I want to set a specific coefficient value for each of the terms
> rather than rely on training. Thus given:
>
> y
> Think you're going to have to explicitly define "hand tailor." I
> haven't a clue what you mean. (Someone else might of course).
Ah, I want to set a specific coefficient value for each of the terms
rather than rely on training. Thus given:
y ~ x0 + x1 + x2 + a
I would like to set:
a =
Think you're going to have to explicitly define "hand tailor." I
haven't a clue what you mean. (Someone else might of course).
-- Bert
On Tue, Nov 12, 2013 at 8:33 AM, wrote:
> Greetings, I'm working on a project where I want to hand-tailor an lm.
> Specifically I want to construct an lm with a
Greetings, I'm working on a project where I want to hand-tailor an lm.
Specifically I want to construct an lm with an existing formula and then
hand tailor the coefficients myself. Is there an established method for
that other than manipulating the $coefficients values?
Thank you,
Colli
7 matches
Mail list logo