George Ho

## Description Running `littlemcmc` in Jupyter notebooks leads to weird behavior. - [ ] All samples are the same - [ ] The PyTorch and JAX models either fail or...

a.k.a. generated quantities in Stan. It would be nice to support them natively somehow (i.e. along with the multiprocessing), and return them inside the `trace` object. We should look at...

The original R post had [four appendices](https://github.com/lindeloev/tests-as-linear/tree/master/simulations), each of which demonstrated (through numerical simulation) that a common statistical test was well-approximated by a linear model. These have not been ported...

Welch's t-test equivalent linear model?

1

See https://eigenfoo.xyz/tests-as-linear/#5.2-Welch%E2%80%99s-t-test The original R post (https://lindeloev.github.io/tests-as-linear/#52_welch%E2%80%99s_t-test) does not go into detail about how to modify the linear model to have different variances.

Subscribe to The Pudding

60

## Paste the link of the GitHub organisation below and submit https://github.com/the-pudding --- ###### Please subscribe to this thread to get notified when a new repository is created

Subscribe to protonmail

30

## Paste the link of the GitHub organisation below and submit https://github.com/protonmail --- ###### Please subscribe to this thread to get notified when a new repository is created

Use `broadcast_to` instead of `broadcast_like`

19

Closes #159. WIP. Two questions: 1. Changing `broadcast_like` to `broadcast_to` in `aesara/tensor/math_opt.py` gives me a lot of `BadOptimization` and `AssertionErrors`, which I'm not knowledgeable enough to debug - can someone...

ArviZ docs should be built off latest release, not master

7

**Describe the bug** As in the title. **To Reproduce** For example, currently [the `plot_forest` doc page](https://arviz-devs.github.io/arviz/generated/arviz.plot_forest.html#arviz.plot_forest) lists the `plot_forest` function to take the `coords` argument, and the little `0.5.1` in...

Support more distributions as random variables

10

Filing this as an issue so we don't forget: https://github.com/pymc-devs/pymc4/pull/41#issuecomment-453775302 I think we can achieve most of the important distributions using `tfp.distributions.Mixture` and `tfp.distributions.Bijector` (e.g. the zero-inflated distributions are just...

TST: test correctness of tfp-unsupported random variables

5

Following up from https://github.com/pymc-devs/pymc4/pull/54#issuecomment-455783915 and https://github.com/pymc-devs/pymc4/pull/54#issuecomment-455866416. We rely on tfp to correctly implement many random variables. However, the random variables that we implement ourselves (e.g. the zero-inflated random variables) need...