Poisson Pseudo-Maximum Likelihood (PPML) Model with Cluster-Robust Standard Errors

In capybara: Fast and Memory Efficient Fitting of Linear Models with High-Dimensional Fixed Effects

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

We will estimate a Poisson Pseudo-Maximum Likelihood (PPML) model using the data available in this package with the idea of replicating the PPML results from Table 3 in @yotov2016advanced.

This requires to include exporter-time and importer-time fixed effects, and to cluster the standard errors by exporter-importer pairs.

The PPML especification corresponds to: \begin{align} X_{ij,t} =& \:\exp\left[\beta_1 \log(DIST){i,j} + \beta_2 CNTG{i,j} +\right.\ \text{ }& \:\left.\beta_3 LANG_{i,j} + \beta_4 CLNY_{i,j} + \pi_{i,t} + \chi_{i,t}\right] \times \varepsilon_{ij,t}. \end{align}

We use dplyr to obtain the log of the distance. This model excludes domestic flows, therefore we need to subset the data also with dplyr.

Required packages:

library(capybara)

We can use the fepoisson() function to obtain the estimated coefficients and we add the fixed effects as | exp_year + imp_year in the formula.

Model estimation:

fit <- fepoisson(
  trade ~ log_dist + cntg + lang + clny + rta | exp_year + imp_year,
  data = trade_panel
)

summary(fit)

The coefficients are almost identical to those in Table 3 from @yotov2016advanced that were obtained with Stata. The difference is attributed to the different fitting algorithms used by the software. Capybara uses the demeaning algorithm proposed by @stammann2018fast.

fit <- fepoisson(
  trade ~ log_dist + cntg + lang + clny + rta | exp_year + imp_year | pair,
  data = trade_panel
)

summary(fit, type = "clustered")

The result is similar and the numerical difference comes fom the variance-covariance matrix estimation method. Capybara clustering algorithm is based on @cameron2011robust.

References

capybara documentation built on April 11, 2025, 5:41 p.m.