-
Currently, discrete distributions support samples, where a specific value of a distribution is chosen at random. However, other stable properties of a distribution are also interesting and could be su…
-
Integrating a function at many points with respect to the empirical distribution requires a large amount of computation.
Is there a good way to get a discrete approximation with few points to an em…
-
Hello,
I noticed that samples have value outside the support for `DiscreteUniform` distribution. Here is a simple reproducible example:
```python
import jax.random
import numpyro
import …
-
related similar issue #2107
The idea is to bring discrete and other future models closer to the GLM pattern of delegating to family and link classes, instead of hardcoding inside the models. This w…
-
The existing univariate distribution infrastructure is an extremely valuable feature of SciPy, and it offers two main ways of interacting with distributions.
1. `stats.norm.pdf(2, loc=0, scale=1)` …
-
Support for censored response data would be useful. The likelihood for the censored data points gets replaced by Pr(a
-
With #1470 we introduce distributions `D` with type parameter `Continuous` which can have atoms, points `a` with `P(X = a) > 0`. There we settled for `pdf(D, a) = P(X = a)` giving the density with res…
-
In some places, like the Gamma function, some effort is made to deal with degenerate
parameters like infinity. I think this is too much effort for a minute use case, as
I don't think users wil…
ghost updated
2 weeks ago
-
https://github.com/statsmodels/statsmodels/issues/7472#issuecomment-853325436
Buddana, Amrutha, and Tomasz J. Kozubowski. 2014. “Discrete Pareto Distributions.” Economic Quality Control 29 (2): 143…
-
This issue was discussed a few times, and I thought there was a github issue on this, but can't seem to find it now.
There is rounding off issue with how the jet energy fractions are saved in nano…