| To: | MAGGIO GUIDO <GUIDO.MAGGIO@ESTERNI.GRUPPO.MPS.IT>, s-news@lists.biostat.wustl.edu |
|---|---|
| Subject: | Re: DIGITS |
| From: | "Richard M. Heiberger" <rmh@temple.edu> |
| Date: | Mon, 19 Dec 2005 07:52:29 -0500 |
You will need to use the log likelihood in all your intermediate calculations. options(digits=20) has an effect on the number of printed decimal positions. It does not change the internal representation, which is 53 bits or approximately 16 decimal digits. See .Machine ?.Machine ?options (look for digits) Rich |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | MIXTURES MODELS, MAGGIO GUIDO |
|---|---|
| Next by Date: | Re: DIGITS, P Ehlers |
| Previous by Thread: | Re: DIGITS, P Ehlers |
| Next by Thread: | MIXTURES MODELS, MAGGIO GUIDO |
| Indexes: | [Date] [Thread] [Top] [All Lists] |