Impact of different conditions on accuracy of five rules for principal components retention
Апстракт
Polemics about criteria for nontrivial principal components are still present in the literature. Finding of a lot of papers, is that the most frequently used Guttman Kaiser's criterion has very poor performance. In the last three years some new criteria were proposed. In this Monte Carlo experiment we aimed to investigate the impact that sample size, number of analyzed variables, number of supposed factors and proportion of error variance have on the accuracy of analyzed criteria for principal components retention. We compared the following criteria: Bartlett's χ2 test, Horn's Parallel Analysis, Guttman-Kaiser's eigenvalue over one, Velicer's MAP and CHull originally proposed by Ceulemans & Kiers. Factors were systematically combined resulting in 690 different combinations. A total of 138,000 simulations were performed. Novelty in this research is systematic variation of the error variance. Performed simulations showed that, in favorable research conditions, all analyzed criteria work ...properly. Bartlett's and Horns criterion expressed the robustness in most of analyzed situations. Velicer's MAP had the best accuracy in situations with small number of subjects and high number of variables. Results confirm earlier findings of Guttman-Kaiser's criterion having the worse performance.
Кључне речи:
principal component analysis / factor retention / criterion for extractionИзвор:
Psihologija, 2013, 46, 3, 331-347Издавач:
- Društvo psihologa Srbije, Beograd
DOI: 10.2298/PSI130801008Z
ISSN: 0048-5705
WoS: 000325004800008
Scopus: 2-s2.0-84886525705
Институција/група
Psihologija / PsychologyTY - JOUR AU - Zorić, Aleksandar AU - Opačić, Goran PY - 2013 UR - http://reff.f.bg.ac.rs/handle/123456789/1765 AB - Polemics about criteria for nontrivial principal components are still present in the literature. Finding of a lot of papers, is that the most frequently used Guttman Kaiser's criterion has very poor performance. In the last three years some new criteria were proposed. In this Monte Carlo experiment we aimed to investigate the impact that sample size, number of analyzed variables, number of supposed factors and proportion of error variance have on the accuracy of analyzed criteria for principal components retention. We compared the following criteria: Bartlett's χ2 test, Horn's Parallel Analysis, Guttman-Kaiser's eigenvalue over one, Velicer's MAP and CHull originally proposed by Ceulemans & Kiers. Factors were systematically combined resulting in 690 different combinations. A total of 138,000 simulations were performed. Novelty in this research is systematic variation of the error variance. Performed simulations showed that, in favorable research conditions, all analyzed criteria work properly. Bartlett's and Horns criterion expressed the robustness in most of analyzed situations. Velicer's MAP had the best accuracy in situations with small number of subjects and high number of variables. Results confirm earlier findings of Guttman-Kaiser's criterion having the worse performance. PB - Društvo psihologa Srbije, Beograd T2 - Psihologija T1 - Impact of different conditions on accuracy of five rules for principal components retention EP - 347 IS - 3 SP - 331 VL - 46 DO - 10.2298/PSI130801008Z ER -
@article{ author = "Zorić, Aleksandar and Opačić, Goran", year = "2013", abstract = "Polemics about criteria for nontrivial principal components are still present in the literature. Finding of a lot of papers, is that the most frequently used Guttman Kaiser's criterion has very poor performance. In the last three years some new criteria were proposed. In this Monte Carlo experiment we aimed to investigate the impact that sample size, number of analyzed variables, number of supposed factors and proportion of error variance have on the accuracy of analyzed criteria for principal components retention. We compared the following criteria: Bartlett's χ2 test, Horn's Parallel Analysis, Guttman-Kaiser's eigenvalue over one, Velicer's MAP and CHull originally proposed by Ceulemans & Kiers. Factors were systematically combined resulting in 690 different combinations. A total of 138,000 simulations were performed. Novelty in this research is systematic variation of the error variance. Performed simulations showed that, in favorable research conditions, all analyzed criteria work properly. Bartlett's and Horns criterion expressed the robustness in most of analyzed situations. Velicer's MAP had the best accuracy in situations with small number of subjects and high number of variables. Results confirm earlier findings of Guttman-Kaiser's criterion having the worse performance.", publisher = "Društvo psihologa Srbije, Beograd", journal = "Psihologija", title = "Impact of different conditions on accuracy of five rules for principal components retention", pages = "347-331", number = "3", volume = "46", doi = "10.2298/PSI130801008Z" }
Zorić, A.,& Opačić, G.. (2013). Impact of different conditions on accuracy of five rules for principal components retention. in Psihologija Društvo psihologa Srbije, Beograd., 46(3), 331-347. https://doi.org/10.2298/PSI130801008Z
Zorić A, Opačić G. Impact of different conditions on accuracy of five rules for principal components retention. in Psihologija. 2013;46(3):331-347. doi:10.2298/PSI130801008Z .
Zorić, Aleksandar, Opačić, Goran, "Impact of different conditions on accuracy of five rules for principal components retention" in Psihologija, 46, no. 3 (2013):331-347, https://doi.org/10.2298/PSI130801008Z . .