1
$\begingroup$

In page 206 of the book 'Elements of statistical learning', the author wrote:

The local log-likelihood for this $J$ class model can be written

$\sum_{i=1}^NK_\lambda (x_0, x_i)\{\beta_{g_i0}(x_0) + \beta_{g_i}(x_0)^T(x_i-x_0) - log[1+\sum_{k=1}^{J-1}exp(\beta_{k0}+\beta_k(x_0)^T(x_i-x_0))]\}$

I can understand that the term $K_\lambda (x_0, x_i)$ is there to weight down the log-likelihood of each individual observation, but really don't know why the term $(x_i-x_0)$ instead of only $x_i$ - which I am expecting.

Is this just a typo or am I misunderstanding something?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

Three bullets below, the authors provide the answer:

enter image description here

Improve this answer
$\endgroup$
1
  • $\begingroup$ I saw it couple days ago, since I cannot vote up now, thanks for your attention $\endgroup$
    – Learner
    Commented Jun 2, 2014 at 4:50

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.