Max Ghenis

`num_children` is null for 98% of records, so we might have to just use `num_children_under18` and skip adult dependents, at least to start. ``` !wget https://github.com/jdebacker/OG-USA-Calibration/raw/master/EarningsProcesses/psid_data_files/psid1968to2015.RData psid = pyreadr.read_r('psid1968to2015.RData')['psid_df'] psid[['head_age',...

I think we can close this and discuss in #9.

Recapping next steps from a meeting with @prrathi: 1. Verify that `head_age`, `spouse_age` and `num_children_under18` are exported from the `psid_download.R` (see comments in #6 on why these are the fields...

The KDE functions and the dependent [`scipy.stats.gaussian_kde`](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.gaussian_kde.html) require probability data. I think we have two options: 1. Smooth with something like LOESS, though I couldn't find a multivariate LOESS smoother...

Actually @prrathi and I realized that we could use the existing KDE function where we model each sxj's share of total children/adults/seniors in the same way that e.g. the share...

Some updates: @prrathi tried the KDE with some PSID data, but it was still noisy because it's the quotient of a smoothed numerator (# kids in bin) and unsmoothed denominator...

Thanks @prrathi. This looks to be due to the logic of 1. Taking `min(head_age)` per `hh_id`, then incrementing it according to the year ([code](https://github.com/PSLmodels/OG-USA-Calibration/blob/8ac4be3c2471cc4d6e9f8b9a82e33a7ac795fec1/ogusa_calibrate/psid_data_setup.py#L57)); in this case, that's `18` 2....

Oh, gotcha. How about linking to the GitHub documentation on them, [Classifying your repository with topics](https://help.github.com/en/github/administering-a-repository/classifying-your-repository-with-topics), and using similar terminology in the criterion, e.g.: >Projects SHOULD classify their repository with...

Just checking in on this. I've come to habitually rely on `black` and been running it as I've been working on unrelated PRs, but if we agree on it, it'd...

This could add consistency to the header with the new site, by replacing the upper left logo