[R] Calculating Deviance from log-likelihood

[Benjamin Dickgiesser]

Hi,

This is a bit R unrelated, I want to, however, use my results from
this in a R function.

I am trying to figure out a formula for the deviance given a
likelihood function. In my derivation I end up with having ln(y-1)
twice in my expression for the deviance (see attached pdf). Which
makes it impossible to calculate a value for the deviance since y can
be = 1.

I know this expression can be simplified differently avoiding ln(y-1).
Does someone have a suggestion?

I would appreciate you help very much!

Thank you,
Benjamin
-------------- next part --------------
A non-text attachment was scrubbed...
Name: deviance.pdf
Type: application/pdf
Size: 31482 bytes
Desc: not available
Url : https://stat.ethz.ch/pipermail/r-help/attachments/20070315/0e45be4f/attachment.pdf