Archive:MANOVA: Difference between revisions

wikademia>Jtneill
mNo edit summary
wikademia>Jtneill
expand
Line 36: Line 36:
# '''Multicollinearity and singularity''' - when there is strong multicollinearity, you have redundant dependent measures and this decreases statistical efficiency  
# '''Multicollinearity and singularity''' - when there is strong multicollinearity, you have redundant dependent measures and this decreases statistical efficiency  
# '''Outliers''' - MANOVA is very sensitive to the effect of outliers because they impact on the Type I error (use Mahalanobis distance to check for multivariate outliers)
# '''Outliers''' - MANOVA is very sensitive to the effect of outliers because they impact on the Type I error (use Mahalanobis distance to check for multivariate outliers)
==How does it work?==
MANOVA combines concepts from [[Factorial ANOVA|factorial ANOVA]] and [[discriminant analysis]]:
* It examines the effect of several independent variables (main effects and interaction effects), as does univariate ANOVA
* These IV effects are examined on several DVs that are combined to form one or more linear composites, as in discriminant analysis.
* Factor A main effect - evaluated by combining the original DVs to form one or more orthogonal discriminant functions (roots) which provide the greatest possible separation of the groups representing the levels of Factor A.
* Factor B main effect - evaluated by combining the original DVs to form one or more orthogonal discriminant functions (roots) which provide the greatest possible separation of the groups representing the levels of Factor B.
* A X B Interaction - assessed by forming one or more discriminant functions that maximise the separation of cells of the factorial data matrix.
* For each effect (A, B, and A x B) the discriminant functions will differ (so the composite DV being examined can change)
==Tests of significance across groups==
These criteria can be used to assess differences across "dimensions" of the DVs
# '''Roy's greatest characteristic root'''
#* tests for differences on only the first discriminant function
#* most appropriate when DVs are strongly interrelated on a single dimension
#* highly sensitive to violation of assumptions - most powerful when all assumptions are met
# Wilk's lambda (''U'')
#* most commonly used statistic for overall significance
#* considers differences over all the characteristic roots
#* the smaller the value of Wilk's lambda, the larger the between-groups dispersion
# Hotelling's trace
#* considers differences over all the characteristic roots
# Pillai's criterion
#* considers differences over all the characteristic roots
#* more robust than Wilk's, should be used when sample size decreases, unequal cell sizes or homogeneity of covariances is violated
==Effect sizes==
Also use [[effect size]]s to evaluate strength of the effects (particularly for significant effects):
* Univariate ANOVA: eta-square gives the proportion of variance in the DV that is attributed to the different levels of the significant IV
* Multivariate ANOVA:  Wilks' Lambda - multivariate eta-square: Wilks' Lambda reflects the ratio of within-group variance across all discriminant functions to total variance across all discriminant functions
==Stepdown analysis==
* Used to assess individually the differences of the DVs
* Procedure involves computing a univariate ''F'' statistic for a DV after eliminating the effects of other DVs preceding it in the analysis.
* Previous DVs are treated as covariates
* Somewhat similar to hierarchical multiple linear regression
* Researcher determines the order in which the DVs are entered, based on some theoretical conceptualisation
* Often used when have correlated dependent variables


==References==
==References==