Cheng Hsiao and Qiankun Zhou "Panel Parametric, Semi-parametric and
Nonparametric Construction of Counterfactuals", Journal of Applied
Econometrics, Vol. 34, No. 4, 2019, pp. 463-481.

There are three empirical applications in the paper.

#####

The First example is the California Tobacco Control Program (CTCP)
data, which is available online from 
https://web.stanford.edu/~jhain/synthpage.html

This panel dataset contains information for 39 US States for the years
1970-2000; see Abadie, Diamond, and Hainmueller (2010) for details.

The variables we use in our paper are: 

The dependent variable is the state level cigarette consumption from 
Abadie et al. (2010).

The control variables are:

Per capita GDP (from Abadie et al. (2010));

The poverty rate, obtained from the National Census Bureau at
https://www.census.gov/data/tables/time-series/demo/income-poverty/historical-poverty-people.html;

Educational Attainment (defined as the percentage of obtaining college
degree of Population 25 Years and Over, obtained from the National
Census Bureau at
https://www.census.gov/topics/education/educational-attainment/data/tables.html

######

The Second example is the impact of CTCP on state level health
expenditure. 

This panel dataset contains information for 39 US States for the years
1970-2000; see Abadie, Diamond, and Hainmueller (2010) for details.

The variables we use in our paper are: 

The dependent variable is the state level health expenditure collected
from the National Health Service (NHS) website

The control variables are:

Per capita GDP (from Abadie et al. (2010));

The poverty rate, obtained from the National Census Bureau at
https://www.census.gov/data/tables/time-series/demo/income-poverty/historical-poverty-people.html,

Educational Attainment (defined as the percentage of obtaining college
degree of Population 25 Years and Over, obtained from the
National Census Bureau at
https://www.census.gov/topics/education/educational-attainment/data/tables.html)

######

The Third example is the Early Day Registration of Xu (2017), and the
data is from Xu (2017), which is available at
https://www.cambridge.org/core/journals/political-analysis/article/generalized-synthetic-control-method-causal-inference-with-interactive-fixed-effects-models/B63A8BD7C239DD4141C67DA10CD0E4F3#fndtn-supplementary-materials

The analysis uses state-level voter turnout data for presidential
elections from 1920 to 2012 (every 4 years). The variable of interest
is Voter turnout (measured in percentage), the controls are Election
Day Registration (a dummy variable), Universal mail-in registration (a
dummy variable) and Motor voter registration (a dummy variable).

######

All data files are .CSV files in DOS format. They are zipped in the
file hz-data.zip. 

Data for replication:

Application 1: smoking.csv
Application 2: smoking-health-expenditure.cswv
Application 3: turnout.csv