How to run regressions on multidimensional panel data in R

Question

I need to run a regression on a panel data . It has 3 dimensions (Year * Company * Country). For example:

============================================
 year | co         


        

Answer 1

I think you can also do:

df <-transform(df, ID = as.numeric(interaction(comp, count, drop=TRUE))) 

And then estimate

result <- plm(value.y ~ value.x, data = df, index = ("ID","year"))

Answer 2

This question is much like these:

• fixed effects in R: plm vs lm + factor()
• Fixed Effects plm package R - multiple observations per year/id

You may not want to create a new dummy, then with dplyr package you can use the group_indices function. Although it do not support mutate, the following approach is straightforward:

fakedata$id <- fakedata %>% group_indices(comp, count)

The id variable will be your first panel dimension. So, you need to set the plm index argument to index = c("id", "year").

For alternatives you can take a look at this question: R create ID within a group.

Answer 3

I think you want to use lm() instead of plm(). This blog post here discusses what you're after:

https://www.r-bloggers.com/r-tutorial-series-multiple-linear-regression/

for your example I'd imagine it would look something like the following:

lm(formula = comp ~ count + year, data = dataname)

Answer 4

If you want to control for another dimension in a within model, simply add a dummy for it:

plm(value.y ~ value.x + count, data = dataname, index = c("comp","year"))

Alternatively (especially for high-dimensional data), look at the lfe package which can 'absorb' the additional dimension so the summary output is not polluted by the dummy variable.