Measurement Invariance: Testing for It and Explaining Why It is Absent
| Autor: | Meitinger, K.M., Davidov, Eldad, Schmidt, Peter, Braun, Michael, Leerstoel Schoot, Methodology and statistics for the behavioural and social sciences |
|---|---|
| Přispěvatelé: | University of Zurich, Meitinger, Katharina, Davidov, Eldad, Schmidt, Peter, Braun, Michael, Leerstoel Schoot, Methodology and statistics for the behavioural and social sciences |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
bias
050109 social psychology Umfrageforschung UFSP13-1 Social Networks Measurement Invariance approximate measurement invariance Bias survey research 0502 economics and business Taverne comparative research 0501 psychology and cognitive sciences comparability lcsh:Social sciences (General) Datengewinnung Social sciences sociology anthropology Alignment 10095 Institute of Sociology Measurement invariance Erhebungstechniken und Analysetechniken der Sozialwissenschaften Sozialwissenschaften Soziologie 300 Social sciences sociology & anthropology 05 social sciences longitudinal study alignment Längsschnittuntersuchung vergleichende Forschung data capture Methods and Techniques of Data Collection and Data Analysis Statistical Methods Computer Methods BSEM ddc:300 lcsh:H1-99 measurement invariance 050203 business & management 3304 Education |
| Zdroj: | Survey Research Methods, 14(4), 345 Survey Research Methods Survey Research Methods, Vol 11, Iss 4 (2018) |
| Popis: | There has been a significant increase in cross-national and longitudinal data production in social science research in recent decades. Before drawing substantive conclusions based on cross-national and longitudinal survey data, researchers need to assess whether the constructs are measured in the same way across countries and time-points. If cross-national data are not tested for comparability, researchers risk confusing methodological artifacts as “real” substantive differences across countries. However, researchers often find it particularly difficult to establish the highest level of measurement invariance, that is, exact scalar invariance. When measurement invariance is rejected, it is crucial to understand why this was the case and to address its absence with approaches, such as alignment optimization or Bayesian structural equation modeling. Survey Research Methods, Vol 14 No 4 (2020): Special Issue: Measurement Equivalence: Testing for It and Explaining Why It is Absent |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|