Zero inflated docs #725
Zero inflated docs #725
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
I would say "parameter" instead of "process" |
|
I would say the example is already looking great! Will review again when it's done but so far I don't have any other suggestions. |
|
Thank you! 👍🏼 If anything, I would like to have the Hurdle poisson section reviewed. In my opinion, the difference between the two is subtle, and I want to make sure my writing makes sense and is intuitive for the users. Thanks! |
Codecov Report
@@ Coverage Diff @@
## main #725 +/- ##
=======================================
Coverage 89.56% 89.56%
=======================================
Files 44 44
Lines 3525 3525
=======================================
Hits 3157 3157
Misses 368 368
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
| @@ -0,0 +1,1905 @@ | |||
| { | |||
There was a problem hiding this comment.
This is a little bit ambiguous: "the probability of the Poisson process, i.e., the probability of non-zero data, increases"
It is correct to say the probability of the Poisson process increases, but that doesn't mean we have no zeroes, since zeroes are also possible under the Poisson distribution.
Reply via ReviewNB
There was a problem hiding this comment.
but that doesn't mean we have no zeroes, since zeroes are also possible under the Poisson distribution.
Yeah, that's why I added the "probability of non-zero data" since it implies that zeros are still plausible. I wanted to add an interpretation of the statement "the probability of the Poisson process" for the users. For some it may be obvious, but for others not. Nonetheless, I updated this paragraph so it is not as ambiguous.
4550eed to
b782b4d
Compare
|
Only one minor last thing (this time it's true!), because all the rest is perfect. Change edit after that, feel free to merge :) |
b782b4d to
a9ab9d3
Compare
|
Thanks for the code reviews on this docs PR. Much appreciated! 😄 |
* zero inflated poisson and hurdle poisson models * grammar fix and sort imports * interpret coeff. and model comparison section * code review changes * change wording in hurdle Poisson section * change posterior predictive bins to use np.arange
* zero inflated poisson and hurdle poisson models * grammar fix and sort imports * interpret coeff. and model comparison section * code review changes * change wording in hurdle Poisson section * change posterior predictive bins to use np.arange
* ordinal model with cumulative link notebook * ordinal model with cumulative link function ordinal models (cumulative and sratio) * unified explanation for cumulative and sequential models * sratio model and data * code review changes * remove intercept in models * zero mu vector prior for sratio family * code review and add section on default priors * explicit explanation of K and k and added summary section * Zero inflated docs (#725) * zero inflated poisson and hurdle poisson models * grammar fix and sort imports * interpret coeff. and model comparison section * code review changes * change wording in hurdle Poisson section * change posterior predictive bins to use np.arange * ordinal model with cumulative link function ordinal models (cumulative and sratio) * use plot_ppc_discrete for posterior predictive samples * add plots explaining the ordinal outcome of the dataset --------- Co-authored-by: Gabriel Stechschulte <gabriel.stechschulte@schindler.com>
* zero inflated poisson and hurdle poisson models * grammar fix and sort imports * interpret coeff. and model comparison section * code review changes * change wording in hurdle Poisson section * change posterior predictive bins to use np.arange
* ordinal model with cumulative link notebook * ordinal model with cumulative link function ordinal models (cumulative and sratio) * unified explanation for cumulative and sequential models * sratio model and data * code review changes * remove intercept in models * zero mu vector prior for sratio family * code review and add section on default priors * explicit explanation of K and k and added summary section * Zero inflated docs (bambinos#725) * zero inflated poisson and hurdle poisson models * grammar fix and sort imports * interpret coeff. and model comparison section * code review changes * change wording in hurdle Poisson section * change posterior predictive bins to use np.arange * ordinal model with cumulative link function ordinal models (cumulative and sratio) * use plot_ppc_discrete for posterior predictive samples * add plots explaining the ordinal outcome of the dataset --------- Co-authored-by: Gabriel Stechschulte <gabriel.stechschulte@schindler.com>
This PR adds documentation for two classes of zero inflated data: (1) Zero inflated poisson (ZIP), and (2) Hurdle poisson.
First, I describe why zero inflated data needs such a class of models followed by a description and implementation of the ZIP and Hurdle models. Then, I describe the differences between the two models.
I am not finished, but it is far enough ahead that I am drafting this PR.