lee: US House elections dataset from Lee (2008)

In xhuang20/rdcqr: Local Composite Quantile Regression Method for Regression Discontinuity

Description

Data on elections to the U.S. House of Representatives

Usage

lee

Format

A data frame with 6,558 rows and 2 variables.

voteshare

the treatment outcome variable y, vote share in the next election

margin

the covariate x, democratic margin of victory at the previous election

Each row

Details

Lee (2008) uses the data on elections to the U.S. House of Representatives (1946-1998) to analyze the incumbency advantage. For a party's candidate who barely won the election (and became incumbent) or barely lost the previous election, their districts usually share many common characteristics. The electoral success for the two groups of common characteristics. The electoral success for the two groups of candidates in the next election can be used to identify the causal incumbency advantage. We subtract the number 50, equivalent to fifty percent, from the vote share data so that the cutoff is 0 for treatment assignment. Each row of the data frame represents a party's candidate.

Source

Mostly Harmless Econometrics data archive at https://economics.mit.edu/faculty/angrist/data1/mhe

References

Lee, D. S. (2008) "Randomized experiments from non-random selection in U.S. House elections," Journal of Econometrics, 142 (2), 675-697.

xhuang20/rdcqr documentation built on July 1, 2021, 5:22 a.m.