On 13/07/19 3:31 PM, Abby Spurdle wrote:
> The distribution of the randomly truncated variable has thus four
> parameters: a, b, mu and sigma. I was able to write down the likelihood
> and attempted to maximise it
I read the Wikipedia article more carefully.
The formula is relatively simple, and is based on the application of
Bayes Theorem.
If one doesn't want to work out the integral, numerical methods can be used.
I am mystified as to what you are saying here. What integral?
As I said, I could write down the likelihood. Explicitly. Maximising
it (numerically *of course*) turned out to be problematic. Back then.
Modern optimisers might help. Presumably the DTDA package has a
reasonable procedure. (I haven't looked at it.)
However, the problem needs to be defined *precisely* first.
Again I have no idea of what you are driving at here. The concept of
"random truncation" is quite precisely defined.
cheers,
Rolf
--
Honorary Research Fellow
Department of Statistics
University of Auckland
Phone: +64-9-373-7599 ext. 88276
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
