This is the dataset used by Imai (2005) to replicate and evaluate the field experiment done by Gerber and Green (2000). The accompanying demo replicates Imai's propensity score model which is then used to estimate the causal effect of get-out-the-vote telephone calls on turnout.
data(GerberGreenImai)A data frame with 10829 observations on the following 26 variables.
Number persons in household
Ward of residence
Asked to commit to voting
Sent mail
Phone batch \#1
Personal contact attempted
Content of message
Personal contact occurred
Number of mailings sent
Age of respondent
Democratic or Republican
Abstained in 1996
Voted in 1996
Phone batch \#2
Voted in 1998
Script read to phone respondents
Contacted by phone in batch \#2
Contacted by phone in batch \#1
Contacted by phone
Phone contact attempted (no blood or blood/civic)
Phone contact attempted (no blood)
Contact occurred in phntrt1
Contact occurred in phntrt2
New voter
Contacted by phone
Age squared
The demo provided, entitled GerberGreenImai, uses Imai's
propensity score model to estimate the causal effect of
get-out-the-vote telephone calls on turnout. The propensity score
model fails to balance age.
Gerber, Alan S. and Donald P. Green. 2000. ``The Effects of Canvassing, Telephone Calls, and Direct Mail on Voter Turnout: A Field Experiment.'' American Political Science Review 94: 653-663.
Gerber, Alan S. and Donald P. Green. 2005. ``Correction to Gerber and Green (2000), replication of disputed findings, and reply to Imai (2005).'' American Political Science Review 99: 301-313.
Imai, Kosuke. 2005. ``Do Get-Out-The-Vote Calls Reduce Turnout? The Importance of Statistical Methods for Field Experiments.'' American Political Science Review 99: 283-300.
Hansen, Ben B. Hansen and Jake Bowers. forthcoming. ``Attributing Effects to a Cluster Randomized Get-Out-The-Vote Campaign.'' Journal of the American Statistical Association.
Also see Match and MatchBalance,
GenMatch, balanceUV, ks.boot
lalonde