Gravity dataset with zero trade flows is an edited version of the full gravity dataset that is used in Head, Mayer, and Ries (2010).
Dataset gravity_no_zeros corresponds to the dataset
without zero trade flows, gravity_zeros, on the other hand,
includes zero trade flows.
In order to have a dataset suited for all functions, a cross-sectional dataset is chosen. All incomplete rows and observations with missing trade flows are therefore excluded from the dataset.
As some of the functions in the package are capable of handling zero
values in trade flows and some are not, two datasets,
gravity_zeros and gravity_no_zeros, are
provided.
The original dataset was downloaded from SciencesPo but the original link is not available anymore. It was edited in the following way:
# 1: Import and read the dataset
# As of 2022年09月25日 the original link from Sciences Po is broken
# I kept the zip on GitHub back in 2017, fortunately
# url <- "http://econ.sciences-po.fr/sites/default/files/file/tmayer/data/col_regfile09.zip"
url <- "https://github.com/pachadotdev/gravity/blob/master/vignettes/col_regfile09.zip?raw=true"
zip <- "col_regfile09.zip"
if (!file.exists(zip)) {
try(download.file(url, zip))
}
try(system("7z e -aos col_regfile09.zip"))
library(haven)
col_regfile09 <- read_dta("col_regfile09.dta")
# 2: Isolation of one year
library(dplyr)
data06 <- col_regfile09 %>%
filter(year == 2006)
# 3: Choosing variables
data06 <- data06 %>%
select(iso_o, iso_d, distw, gdp_o, gdp_d, rta, flow, contig, comlang_off, comcur)
# 4: Isolation of complete cases
library(tidyr)
gravity_zeros <- data06 %>%
drop_na()
# 5: Exclusion of trade flows equal to 0
gravity_no_zeros <- gravity_zeros %>%
filter(flow > 0)
# 6: Export the data
save(gravity_zeros, file = "gravity_zeros.rdata", compress = "xz")
save(gravity_no_zeros, file = "gravity_no_zeros.rdata", compress = "xz")