Hello
In the old version of stan user Manualhttps://mc-stan.org/docs/2_20/functions-reference/cumulative-distribution-functions.html
However in the new versionhttps://mc-stan.org/docs/functions-reference/conventions_for_probability_functions.html#cumulative-distribution-functions
Which one of these is actually implemented in Stan ? Does CCDF include P [Y=y] ?
Thanks in advance
That old version (2.20) is very old, and even the next old version (2.21) uses the newer definition .
stan-dev:master ← mcol:issue_71
opened 07:39PM - 21 Sep 19 UTC
#### Submission Checklist
- [X] Builds locally
- [X] Declare copyright hold… er and open-source license: see below
#### Summary
Fixes #71.
#### Copyright and Licensing
Please list the copyright holder for the work you are submitting (this will be you or your assignee, such as a university or company):
Marco Colombo
By submitting this pull request, the copyright holder is agreeing to license the submitted work under the following licenses:
- Code: BSD 3-clause (https://opensource.org/licenses/BSD-3-Clause)
- Documentation: CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
1 Like
It should be Pr[Y > y] = 1 - Pr[Y <= 1]. We should have CDF(y) + CCDF(y) = 1.
Of course, for continuous variables, the distinction doesn’t matter as it’s just a difference of a single point, which has measure zero in a continuous density.