Panel data set of 261 cities in China from 2009 to 2021 (partial indicators)
Description
Dataset title Panel Data for “Digital-Economy Development and Urban Human Capital: Evidence from China’s Big-Data Pilot Zones” Description This dataset supports the empirical analyses in the above-titled article. It is a balanced panel of 261 Chinese prefecture-level cities covering 2009-2021 (N = 3 393) observations. File(s) panel_desensitized.dta – Stata 17 data file; string identifiers for provinces and cities have been replaced by numeric codes (prov_id, city_id) to ensure anonymity. Key variables HCI (log of tertiary-student enrolment), digital (policy dummy for Big-Data Pilot Zones), PGDP, ISU, FDL, OPEN, FDI, DI, EDU (controls), and TI (regional innovation). Missing values (<1 %) are filled via linear interpolation; all monetary figures are deflated to 2015 CNY. Data sources China City Statistical Yearbook; China Education Statistical Yearbook; EPS Database; authors’ calculations. Licence & citation Released under CC BY 4.0. Please cite this dataset as Mendeley Data, DOI: 10.17632/xxxxxxxx.v1 when using or replicating the study.
Files
Steps to reproduce
1.Files. Download panel_desensitized.dta and replication.do to the same working directory. 2.Software. Run Stata 17 (or newer). The script automatically checks and, if necessary, installs the user-written packages reghdfe, psmatch2, and partialout. 3.Execution. At the Stata prompt type:do code.do The script will (i) load the panel dataset (261 cities × 13 years, 2009–2021); (ii) reconstruct all study variables; (iii) estimate baseline DID, PSM-DID, and double machine-learning models; (iv) generate every table and figure reported in the associated article, saving outputs to a folder named Results. No raw identifiers are included; province and city names were replaced by numeric IDs before upload. Re-running the single .do file fully reproduces the empirical results.