Sebastian Kripfganz and Claudia Schwarz, "Estimation of Linear Dynamic
Panel Data Models with Time-Invariant Regressors", Journal of Applied
Econometrics, Vol. 34, No. 4, 2019, pp. 526-546.

All data and a Stata replication file are included in the zip file
"ks-files.zip". The data set comes in an ASCII version with
comma-separated values and variable names in the first row
("data.csv") and a Stata version ("data.dta"). The replication file is
a Stata do-file ("ks-jae.do").

The data files contain variables with 2,767 observations from two sources:

1) Peter Egger and Michael Pfaffermayr, "Distance, Trade, and FDI: A
Hausman-Taylor SUR Approach", Journal of Applied Econometrics, Vol.
19, No. 2, 2004, pp. 227-246.

We use all the variables (except lrex) from their "data_us.dta" file
that are described at
http://qed.econ.queensu.ca/jae/2004-v19.2/egger-pfaffermayr/readme.ep.txt

2) Thierry Mayer and Soledad Zignago (2011). "Notes on CEPII's
distances measures: The GeoDist Database." CEPII Working Paper
2011-25.

We use the following variables from their "dist_cepii.dta" file:

. contig:        1 for contiguity
. comlang_off:   1 for common official of primary language
. comlang_ethno: 1 if a language is spoken by at least 9% of the population
                   in both countries
. colony:        1 for pairs ever in colonial relationship

The following variable is created from the above:

. comlang_other: comlang_ethno*(1-comlang_off)

The order of the variables in the data files is:

codeim ind year contig comlang_off comlang_ethno colony comlang_other
lrfdi lgdt lsimi lrk lrh lrl ldist lkgdt lkldist

The Stata replication file uses community-contributed programs that
can be installed from the Boston College Statistical Software
Components (SSC) archive by typing the following in Stata's command
window:

. ssc install xtseqreg
. ssc install xtdpdqml
. ssc install xtdpdgmm

Sebastian Kripfganz
S.Kripfganz [AT] exeter.ac.uk