Putting ‘political’ back in political trust: an IRT test of the unidimensionality and cross-national equivalence of political trust measures

被引:8
作者
van der Meer T.W.G. [1 ]
Ouattara E. [1 ]
机构
[1] Department of Political Science, University of Amsterdam, Amsterdam
关键词
Comparative analysis; Item response theory; Measurement equivalence; Political trust; Rasch modelling; Trust in government;
D O I
10.1007/s11135-019-00913-6
中图分类号
学科分类号
摘要
Much research intro political trust—its causes, correlates and trends—builds on the twin assumptions that trust in a wide range of political institutions is ultimately an expression of (1) a singular and (2) a cross-nationally equivalent underlying attitude. Yet, the widespread assumptions of unidimensionality and cross-national equivalence of political trust is at odds with the dominant conceptual understanding of political trust as a relational concept, driven by subjects, objects, and their interplay. This paper employs Rasch modelling as a direct, strict test of unidimensionality, equivalence and item hierarchy. We test the fit of the Rasch model on political trust items in seven widely used, cross-national surveys (World Values Survey, Afrobarometer, Arabbarometer, Asian Barometer, Eurobarometer, European Social Survey, and Latinobarometro), covering 161 national surveys in 119 countries across the globe. We find that the unidimensional specification of the Rasch model does not fit the standard political trust question batteries. Political trust is not cross-nationally equivalent; trust in specific political institutions is more than a mere indicator of an underlying attitude. This conclusion does not impede cross-national research into political trust; rather it illustrates the need for consistent robustness checks across a range of objects of political trust. Our findings open up new venues for substantive research questions on specific objects of political trust and their relationships. © 2019, The Author(s).
引用
收藏
页码:2983 / 3002
页数:19
相关论文
共 62 条
  • [11] Cai L., Two-tier item factor analysis modeling, Handbook of item response theory, 1, pp. 421-435, (2016)
  • [12] Cai L., Thissen D., Nominal categories models, Handbook of item response theory, 1, pp. 79-102, (2016)
  • [13] Chalmers P., mirt: a multidimensional item response theory package for the R environment, J. Stat. Softw., 48, pp. 1-29, (2012)
  • [14] Choi Y.-T., Kwon G.-H., New forms of citizen participation using SNS: an empirical approach, Qual. Quant., 53, pp. 1-17, (2019)
  • [15] Citrin J., Stoker L., Political trust in a cynical age, Annu. Rev. Political Sci., 21, pp. 2.1-2.22, (2018)
  • [16] Coromina L., Davidov E., Evaluating measurement invariance for social and political trust in Western Europe over four measurement time points (2002–2008), ASK Res. Methods, 22, pp. 37-54, (2013)
  • [17] Dalton R.J., Political trust in North America, Handbook on political trust, pp. 375-394, (2017)
  • [18] Davidov E., Meuleman B., Cieciuch J., Schmidt P., Billiet J., measurement equivalence in cross-national research, Annu. Rev. Sociol., 40, pp. 55-75, (2014)
  • [19] De Vries C.E., van Kersbergen K., Interests, identity and political allegiance in the European Union, Acta Polit., 42, pp. 307-328, (2007)
  • [20] De Vroome T., Hooghe M., Marien S., The origins of generalized and political trust among immigrant minorities and the majority population in the Netherlands, Eur. Sociol. Rev., 29, pp. 1336-1350, (2013)