[R] ACF normalization.

[alok juneja]

Hi,

My earlier email was sent as html so no visible properly. I am now posting it as text. Sorry for the duplication of the message.


Can anyone please provide the formula used to compute ACF(nlme). I believe the one that is used in R is of the type mentioned on the website (http://www.itl.nist.gov/div898/handbook/eda/section3/autocopl.htm). Please correct me if I am wrong. The normalization of the numerator (Ch)
has been done by 'N' where as I would like to do it by 'N-k'. Is there
anyway in the present implementation of ACF to normalize it by 'N-k',
where 'N' is the total number of observations and 'k' is the lag. 

Best
Alok