Re: large negative parameter correlations in regression


Anon. wrote:
Reef Fish wrote:
Anon. wrote:
Reef Fish wrote:

<snip>

this: "If you mean-centred your variables, then the correlation will go
away." Again, falsifiable.
It's not only falsifiable, it is FALSE.
OK, prove it.
Then you would NOT have an intercept, you IDIOT!

The keyword is

"if you mean-centered your variables" ALL the variables.

I had meant covariates, but it still doesn't matter. You will still
have an intercept in the model.

How would you ESTIMATE a parameter that is nonexistent?

OK, the point estimate from the centred
data will be zero,

Can't blame it on Finnish, because you are an ignorant BRIT!
"nonexistent" and "zero" are not synonymous.

If there is no intercept parameter to estimate, and you
decided to put a zero there doesn't mean that it has been
estimated.

but it will have a standard error about it, because
it's still being estimated.

Why don't YOU tell us that the standard error is?

So, you still have to demonstrate that I'm wrong I'm afraid.

You've been given too many FREE lessons for your ridiculous
comments to the OP.

You had been PROVEN wrong already about your "mean-center"
nonsense. And even if you could come up with some other
related nonsense, this reply will KILL ALL:

You cannot possibly GAIN anything that you don't already KNOW
by mean centering the variables you used, because that is only
a trivial reprametrization of the additive kind.

You have NO new insight.

You have NO new information you couldn't have gotten from the old.

You have ... the typical Bob O'Hara usefulness in Bob O'Hara
comments on statistical matters -- NOTHING.

-- Reef Fish Bob.

.