search

QuantEcon / lecture-python.myst

Quantitative Economics with Python
https://python.quantecon.org
81 stars 43 forks source link

AR1 Bayes lecture comments #252

Open jstac opened 2 years ago

jstac commented 2 years ago

@thomassargent30 @smit-create, I really enjoyed reading the lecture https://python.quantecon.org/ar1_bayes.html

Some minor suggestions:

It is not clear from reading the lecture why we are using both pymc and numpyro. Is it because they give different insights or because we want to show how to use both libraries? Some guidance for the reader would be helpful.

It would help the reader if there was a bit more guidance about the numpyro implementation. E.g., what is NUTS? Just one or two lines, and perhaps a few links?

Add "the" to "The first component of statistical model"

Smit-create commented 2 years ago

Hi @jstac Thanks for opening up this issue. I'll try to go through the lecture once and modify it according to your suggestions.

It is not clear from reading the lecture why we are using both pymc and numpyro. Is it because they give different insights or because we want to show how to use both libraries? Some guidance for the reader would be helpful.

Taking a very high-level look at the lecture, it seems that we are trying to show how to use two different libraries to solve the same problem (not sure).

jstac commented 2 years ago

Thanks @Smit-create . @thomassargent30 let me know that he plans to address these comments