Multivariate models for pretest posttest data and a comparison to univariate models

Kleine Bardenhorst, S. (2017) Multivariate models for pretest posttest data and a comparison to univariate models.

[img]
Preview
PDF
441kB
Abstract:The pretest-posttest control group design is a popular design and frequently discussed in the literature. In this study multivariate models are investigated for pretest posttest data and a comparison is made with univariate methods, the change score method and the regressor variable method. Three simulation studies were con- ducted to investigate differences. The first study provides a basic comparison, while the second study focuses on the investigation of heterogeneous treatment effects. In the third simulation study, the analyses of two dependent variables are investigated. The results showed no significant differences between univariate and multivariate methods in the studies one and two. Nevertheless, the third study showed that the multivariate method provides higher power and a better Type-1 error rate compared to univariate methods when investigating two dependent variables. The multivariate method can provide better results in analyzing multivariate pretest posttest data, when compared to the univariate methods.
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/71682
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page