Replication Data for: Self-Censorship of Regime Support in Authoritarian States: Evidence from list experiments in China

In this repository you'll find the dataset and code to reproduce all analysis in both the paper and the online appendix.

All analysis is done in R (v. 3.5.1), in addition to base R the following packages are needed to reproduce all files:
- 'tidyverse'
- 'list'
- 'xtable'
- 'rio'
- 'texreg'

The code is annotated to improve readability. To reproduce tables and figure please.

1. run **main-analysis.R** (which calls main-estimates.R) to produce main estimates and output for *figure 2*, *table 7* and *table 8*

2. run **subgroup-analysis.R** (which calls subgroup-system.R, subgroup-censor.R, subgroup-corruption.R and subgroup-confidence.R,) to produce estimates and output for *figure 4*

3. run **no-design-effect** to produce *table 5* and *6*.