CapyBara V1.8.0 is now available on Cran | R-Bloggers

Due to delays with my stock market payment, if this message is useful for you, I kindly request a minimal donation Buy a coffee for me. It will be used to continue my open source efforts. The complete explanation is here: A personal message from an Open Source employee. If you play the electric guitar, the same stock market chaos led me to make my guitar pedals and do it -self -kits hobby in a company, and you can check it here.

CapyBara started as an alpaca clone that uses CPP11armadillo To be a fast and small footprint software to fit GLMs with fixed effects of K-Way.

The software can estimate GLMs from the exponential family and also negative binomial models, using a humiliating/centering approach that offers a large gear for models of a large number of fixed effects.

Here is a small benchmark for the next specification using a model from An advanced guide for analysis of trade policy:

Where:

To obtain the model coefficients, I used the following formula with fixed effects:

form <- trade ~ rta + rta_lag4 + rta_lag8 + rta_lag12 +
  intl_border_1986 + intl_border_1990 + intl_border_1994 +
  intl_border_1998 + intl_border_2002 |
  exp_year + imp_year + pair_id_2

I used the same formula with alpaca, fixest and capybara and the data set of AgtpaGive me and memory results in the next time:

Capybara would not exist without alpaca and it is currently slower than Fixest. Although CapyBara can be improved, I am happy with current memory efficiency.

You can install the current CapyBara -stable version with:

install.packages("capybara")

The official documentation is here.

I hope this is useful 🙂

Related