Replication data for: No News is News: Non-Ignorable Non-Response in Roll-Call Data Analysis
Harvard Dataverse (Africa Rice Center, Bioversity International, CCAFS, CIAT, IFPRI, IRRI and WorldFish)
View Archive InfoField | Value | |
Title |
Replication data for: No News is News: Non-Ignorable Non-Response in Roll-Call Data Analysis
|
|
Identifier |
https://doi.org/10.7910/DVN/26457
|
|
Creator |
Rosas, Guillermo
Shomer, Yael Haptonstahl, Stephen |
|
Publisher |
Harvard Dataverse
|
|
Description |
Roll-call votes are widely employed to infer the ideological proclivities of legislators. However, many roll-call matrices are characterized by high levels of non-response. Under many circumstances, non-response cannot be assumed to be ignorable. We examine the consequences of violating the ignorability assumption that underlies current methods of roll-call analysis. We present a basic estimation framework to model non-response and vote choice concurrently, build a model that captures the logic of competing principals that underlies accounts of non-response in many legislatures, and illustrate the payoff of addressing non-ignorable non-response through simulations and actual data. We conclude that modeling presumed patterns of non-ignorable non-response can yield important inferential payoffs over current models that assume random missingness, but we also emphasize that the decision to model non-response should be based on theoretical grounds since one cannot rely on measures of goodness of fit for the purpose of model comparison.
|
|
Subject |
Social Sciences
Missing data Voting abstention Item-response theory Roll-call data Bayesian inference |
|
Date |
2014-06
|
|
Contributor |
Guillermo Rosas
|
|
Type |
roll-call votes, program source code
|
|