Power rates of two robust approaches to the analysis of longitudinal data
Fuente:
Redalyc
Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Universitat de València
2003
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1876476387889512448 |
|---|---|
| author | M. Ato |
| author_facet | M. Ato |
| contents | Power rates of two robust approaches to the analysis of longitudinal data M. Ato G. Vallejo P. Fernández Psicología Power rates of two robust approaches for the analysis of longitudinaldata. The purpose of this paper was to compare the power of two of thenewest, and perhaps more robust, approaches among current availableprocedures for analyzing longitudinal data, when dispersion matrices wereunequal across groups. In particular, the sensibility of the improvedmultivariate Brown-Forsythe approach was compared to the linear mixedmodel procedure, with the residual degrees of freedom based onSatterthwaites technique for matching moments in a longitudinal designinvolving one grouping factor and one repeated-measures factor. The resultsindicate that the power value of the mixed-model approach was higher thanthe one observed in the Brown-Forsythe procedure for the repeatedmeasuresmain effects, particularly when the sample size was small. Wheninteraction effects were the focus of interest, a similar pattern of results wasobtained; however, being the differences less marked under this condition. 2003 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16924107 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.1 Vol.24 |
| format | Artículo científico |
| id | redalyc_16924107 |
| institution | Redalyc |
| language | en |
| publishDate | 2003 |
| publisher | Universitat de València |
| spellingShingle | Power rates of two robust approaches to the analysis of longitudinal data M. Ato Psicología Power rates of two robust approaches to the analysis of longitudinal data M. Ato G. Vallejo P. Fernández Psicología Power rates of two robust approaches for the analysis of longitudinaldata. The purpose of this paper was to compare the power of two of thenewest, and perhaps more robust, approaches among current availableprocedures for analyzing longitudinal data, when dispersion matrices wereunequal across groups. In particular, the sensibility of the improvedmultivariate Brown-Forsythe approach was compared to the linear mixedmodel procedure, with the residual degrees of freedom based onSatterthwaites technique for matching moments in a longitudinal designinvolving one grouping factor and one repeated-measures factor. The resultsindicate that the power value of the mixed-model approach was higher thanthe one observed in the Brown-Forsythe procedure for the repeatedmeasuresmain effects, particularly when the sample size was small. Wheninteraction effects were the focus of interest, a similar pattern of results wasobtained; however, being the differences less marked under this condition. 2003 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16924107 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.1 Vol.24 |
| title | Power rates of two robust approaches to the analysis of longitudinal data |
| topic | Psicología |
| url | https://www.redalyc.org/articulo.oa?id=16924107 |