University of Twente Student Theses

Login

Intra-Class Correlation Testing to Examine Intra-Group Differences

Jongmans, I.G.M. (2021) Intra-Class Correlation Testing to Examine Intra-Group Differences.

[img] PDF
1MB
Abstract:Hierarchical data structures are the norm in educational and social sciences. The intraclass correlation coefficient (ICC) quantifies the relative variation explained by clustering observations in groups (Snijders & Bosker, 2011). The ICC is used to measure the strength of the hierarchical dependence, but the ICC might have more to offer than its conventional use. The ICC is studied as a tool for the measurement for intra-group differences. In a simulation study, the performance of the ICC Bayes factor (BF) test of Mulder and Fox (2019) is examined for different sample sizes. For small sample sizes, the BF test showed accurate results. Furthermore, a real data trial run for the ICC test was performed on the FOCUS data (van Geel, Keuning, Visscher & Fox, 2016). The conclusion, the ICC does convey intra-group differences and offers additional information to the mean scores in nested data. Furthermore, the ICC test can process the ICC, even when it becomes negative, to a sufficient degree. Bearing in mind that, the evidence categories used and thus the BF values of the test require further investigation when testing the ICC.
Item Type:Essay (Bachelor)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:77 psychology
Programme:Psychology BSc (56604)
Link to this item:http://purl.utwente.nl/essays/85582
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page