fixest | Fixed-effects estimations

I can't replicate your example with the provided code. Neverthless, you can use a loop like this:

edit: plm version 2.6-0 has the fast mode enabled by default. A further speed up for plm is gained if package fixest (or lfe) is also installed. For the benchmarked example in ?plm.fast, this gives a speed up to a 28x speed-up.

old answer Since version 2.4-0 of plm, there is an optional fast mode, see the NEWS entry for 2.4-0 and 2.4-2: https://cran.r-project.org/web/packages/plm/news/news.html

To enable the fast mode, set this option:

options("plm.fast" = TRUE)

You can set this option manually, in your script, or in your .Rprofile file.

You will need to have package collapse installed as well, optionally package fixest or lfe for further speed up for some cases, esp. two-ways fixed effects from plm 2.4-2 onwards.

For a benchmarked example, see the help for ?plm.fast.

In your example, much time is spent to create a pdata.frame (the data format plm uses), it happens implicitly in the call to plm if the data is not explicitly converted first. So, one could split out the formating to pdata.frame and the model estimation. So, the execution time of plm() is significantly smaller. Also, this would speed up any further model estimation after the first one on the data set.

Set family, fml and fml_all to NULL and it should work.

The issue is that these items refer to environments even though they do not include the environments. However, when save is applied, the environments to which these values refer are also saved, leading to the large file size.

This is an issue I'll try to solve in the package. Btw the items linear.predictors and working_residuals will be appropriately erased in the next version of the package (0.10.2).

It works. It's likely a version problem:

UPDATE: I have no idea why I missed the label argument. Anyway, @laurent-bergé is more correct.

NOTE: This answer is translated from my original post (in Japanese).

I guess fixest package have no options for the cross references on Rmd. Although it may be a kind of kludge, I found that you can insert LaTeX command in the title argument like the following.

So, fixest_mult has a pretty strange setup as I delved deeper. As you noticed, mapping across it or using apply just accesses part of the data frames. In fact, it isn't just the data frames for "Ozone", but actually just the data frames for the first 6 data frames (those for c("Full sample", "5", "6").

If you convert to a list, it access the data attribute, which is a sequential list of all 12 data frames, but dropping the relevant names you're looking for. So, as a workaround, could use pmap() and the names (found in the attributes of the object) to tidy() and then use mutate() for your desired columns.

There is a degrees_freedom

Response from the dev: there's no way to manually drop one.

There are two issues, here.

1. In the lm() model, the period variable is interacted, but treated as a continuous numeric variable. In contrast, calling i(period, treat) treats period as a factor (this is explained clearly in the documentation).
2. The i() function only includes the interactions, and not the constitutive terms.

Here are two models to illustrate the parallels: