Re: multiple linear regression


There are two important things to know about centering:

(1) Centering has NO effect on tests of significance. You should get
numerically identical t-statistics on the centered and uncentered
data.

Hmm, that seems to contradict what Ray just wrote doesn't it? If
centering x2 changes b1, then how can it not alter the test of
significance on b1 (since it presumably doesn't alter the standard
error associated with b1)?
.

Relevant Pages

  • Re: multiple linear regression
    ... numerically identical t-statistics on the centered and uncentered ... centering x2 changes b1, then how can it not alter the test of ... significance on b1 (since it presumably doesn't alter the standard ... subtract a constant from the variable the coefficient doesn't change. ...
    (sci.stat.consult)
  • Re: multiple linear regression
    ... numerically identical t-statistics on the centered and uncentered ... centering x2 changes b1, then how can it not alter the test of ... significance on b1 (since it presumably doesn't alter the standard ... but it does change the standard error...by exactly enough to keep ...
    (sci.stat.consult)
  • Re: multiple linear regression
    ... Centering has NO effect on tests of significance. ... numerically identical t-statistics on the centered and uncentered ... significance on b1 (since it presumably doesn't alter the standard ... but it does change the standard error...by exactly enough to keep ...
    (sci.stat.consult)