Mountain View
biomedical and healthCAre Data Discovery Index Ecosystem
help Advanced Search
Title: Replication data for: Validating estimates of latent traits from textual data using human judgement as a benchmark      
dateReleased:
10-02-2014
downloadURL: http://hdl.handle.net/1902.1/20387
ID:
hdl:1902.1/20387
description:
Automated and statistical methods for estimating latent political traits and classes from textual data hold great promise, since virtually every political act involves the production of text. Statistical models of natural language features, however, are heavily laden with unrealistic assumptions about the process that generates this data, including the stochastic process of text generation, the functional link between political variables and observed text, and the nature of the variables (and dimensions) on which observed text should be conditioned. While acknowledging statistical models of latent traits to be “wrong”, political scientists nonetheless treat the treat their results as sufficiently valid to be useful. In this paper, we address the issue of substantive validity in the face of potential model failure, in the context of unsupervised scaling methods of latent traits. We critically examine one popular parametric measurement model of latent traits for text and then compare its results to systematic human judgments of the texts as a benchmark for validity.
description:
Lowe, Will; Benoit, Kenneth, 2013, "Replication data for: Validating estimates of latent traits from textual data using human judgement as a benchmark", http://hdl.handle.net/1902.1/20387, Harvard Dataverse, V2
name:
Lowe, Will
Benoit, Kenneth
homePage: http://www.harvard.edu/
name:
Harvard University
ID:
SCR:011273
abbreviation:
DataVerse
homePage: http://thedata.org/
name:
Dataverse Network Project
ID:
SCR:001997