CoChat
Sign Up
Cited by 381Computational and Text Analysis MethodsElectoral Systems and Political ParticipationGame Theory and Voting Systems

Measuring Group Differences in High‐Dimensional Choices: Method and Application to Congressional Speech

Gentzkow, Matthew, Shapiro, Jesse M., Taddy, Matt·2019·Econometrica
DOI 10.3982/ecta16566
Open this paper in CoChat — free account

Abstract

We study the problem of measuring group differences in choices when the dimensionality of the choice set is large. We show that standard approaches suffer from a severe finite‐sample bias, and we propose an estimator that applies recent advances in machine learning to address this bias. We apply this method to measure trends in the partisanship of congressional speech from 1873 to 2016, defining partisanship to be the ease with which an observer could infer a congressperson's party from a single utterance. Our estimates imply that partisanship is far greater in recent years than in the past, and that it increased sharply in the early 1990s after remaining low and relatively constant over the preceding century.

Integrity signals

Registry

Crossref · 10.3982/ecta16566

Cites

83 of 83 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Greater polarization is evident in the content of political speech used by Democratic and Republican legislators in the 1990s and especially the 2000s.

    “In the 1990s and especially the 2000s, greater polarization is also evident in the content of political speech used by Democratic and Republican legislators (Gentzkow, Shapiro, and Taddy 2019).”

    From Importing Political Polarization? The Electoral Consequences of Rising Trade Exposure (2020) · cites this paper as Gentzkow, Shapiro, and Taddy 2019

  • The paper uses a variant of covariate assignment shuffling suggested by Gentzkow, Shapiro, and Taddy (2019) to compute empirical p-values.

    “To do this, we use a variant of covariate assignment shuffling suggested by Gentzkow, Shapiro, and Taddy (2019).”

    From Embedding Regression: Models for Context-Specific Description and Inference (2023) · cites this paper as Gentzkow, Shapiro, and Taddy (2019)

Cites

Flagged first, then by citations

Research works printed but not linked: 5

  1. Frantzich, 1996, The C-SPAN Revolution
  2. Gentzkow, M., B. T. Kelly, and M. Taddy “Text as Data,” Journal of Economic Literature (Forthcoming).
  3. Gingrich, 1994, Contract With America
  4. Orwell, 1946, Horizon, 13, 252
  5. Palmgren, 1981, Biometrika, 68, 563

Cited by

Sorted by citations

Related

Authors
Gentzkow, M., Shapiro, J. M., & Taddy, M.
Affiliations
  • National Bureau of Economic Research (US)
  • Amazon (United States) (US)
ORCID
Gentzkow, Matthew
Venue
Econometrica
Publisher
The Econometric Society
Published
2019
Volume
87
Issue
4
Pages
1307-1340
ISSN
0012-9682 (ISSN-L)
DOI
10.3982/ecta16566
OpenAlex
W3022516804
Semantic Scholar
3c8f44c82136ab46893541c8f2324a0a40a1a903
Cited by
381
References
81
Citations by year
2026: 45 · 2025: 63 · 2024: 55 · 2023: 68 · 2022: 52 · 2021: 43 · 2020: 34 · 2019: 15 · 2018: 3 · 2017: 2 · 2015: 1
FWCI
109.50
Type
journal article
Language
en
Open access
closed
Locations
Econometrica (publishedVersion)
Topics
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Social Sciences › Political Science and International Relations › Electoral Systems and Political Participation
  • Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Game Theory and Voting Systems
Keywords
finite-sample bias, machine learning estimators, congressional speeches, partisanship, party identification, political speeches

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review