Cited by 273Qualitative Comparative Analysis ResearchBayesian Modeling and Causal InferenceComputational and Text Analysis Methods

Crisp-Set Qualitative Comparative Analysis (csQCA), Contradictions and Consistency Benchmarks for Model Specification

Open access
Marx, Axel, Dusa, Adrian·2011·Methodological Innovations Online

Abstract

The purpose of this paper is to address and test two assumptions on which csQCA is based, namely that csQCA will generate contradictions and low consistency scores if models are ill-specified. The first part of the paper introduces csQCA in general and as a stepwise approach. In a second part a real-life example is introduced with the purpose of illustrating how csQCA operates and as an input for a simulation in the subsequent part. The third part introduces contradictions, consistency, their interrelatedness and the assumptions which are made with regard to contradictions and consistency. Subsequently the assumptions are tested via a simulation on the basis of a csQCA analysis of over 5 million random datasets. The paper argues that researchers cannot always assume that csQCA will generate contradictions or low consistency scores when models are ill-specified. Such an assumption is only justified when csQCA applications take limitations with regard to model specification (the number of conditions and the number of cases) into account. Benchmark tables for model specification purposes are developed. Since these tables are based on a probability value of 0.5 the paper also tests the results for contradictions and consistency for the probabilities which were present in a real-life example. This test shows that the 0.5 probability generates an appropriate measure for the occurrence of contradictions and consistency indicating that the benchmark tables can be used for different applications with different distributions of 0's and 1's in the conditions and outcomes. The paper ends with a conclusion.

Integrity signals

Registry

Crossref · 10.4256/mio.2010.0037

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

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

Claims the paper makes

We couldn’t retrieve this paper’s full text, 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?

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Marx, A., & Dusa, A.
Affiliations
  • KU Leuven (BE)
  • Department of Sociology, University of Bucharest
Corresponding author
Marx, Axel
Venue
Methodological Innovations Online
Published
2011-08
Volume
6
Issue
2
Pages
103-148
ISSN
1748-0612 (ISSN-L)
OpenAlex
W2292863806
Cited by
273
References
50
Citations by year
2026: 19 · 2025: 15 · 2024: 33 · 2023: 33 · 2022: 26 · 2021: 31 · 2020: 16 · 2019: 21 · 2018: 21 · 2017: 10 · 2016: 16 · 2015: 16 · 2014: 8 · 2013: 7 · 2012: 1
FWCI
17.13
Type
journal article
Language
en
Open access
Locations
  • Methodological Innovations Online (publishedVersion, cc-by-nc)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Sociology and Political Science › Qualitative Comparative Analysis Research
  • Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
contradiction, consistency, model specification, simulation study, stepwise approach, configurational comparative methods

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