Class Note for SW 983 at KU
Popular in Course
Popular in Department
This 1 page Class Notes was uploaded by an elite notetaker on Friday February 6, 2015. The Class Notes belongs to a course at Kansas taught by a professor in Fall. Since its upload, it has received 23 views.
Reviews for Class Note for SW 983 at KU
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 02/06/15
SW 983 LECTURE NOTES MANOVA MANOVA is used to analyze the difference between groups on two or more dependent variables simultaneously Assumes that the dependent variables considered together make sense as a group ie they are correlated It is a logical and simple extension of the ttest one metric dependent variable and two groups and univariate ANOVA one metric dependent variable and three or more groups and involves the same underlying statistics as discriminant analysis The MANOVA model can be extended to factorial designs and inclusion of covariates MANCOVA just as in ANOVA Thus much in this material should look familiar Conceptual reasons for preferring a multivariate analysis 0 This situation multiple dependent variables arises quite naturally in our work Most of our programs attempt to impact multiple aspects of a clients functioning and environment 0 Through the use of several criterion measures we can obtain a more complete and detailed description of the phenomenon under investigation Statistical reasons for preferring a multivariate analysis Univariate tests lead to in ated overall type I error rate Univariate tests ignore correlations among the dependent variables Multivariate test has greater power Multivariate avoids cancelling out of effects that may occur when total score used MANOVA and Discriminant Analvsis Multivariate significance indicates that there is a linear combination of the dependent variables referred to as the discriminant function 7 see eq6 1 that captures significant variation between the groups The linear combination may not always be interpretable conceptually or statistically or the researcher may be more interested in the specific variables rather than a combination of them This leads to post hoc univariate tests In MANOVA the researcher is interested in group differences as the outcome or dependent variables The MANOVA model allows the researcher to explore the contribution of variables including membership in possibly experimental groups and combinations of other metric and nonmetric independent variables to explaining variance in a group of metric dependent variables In DA the researcher is interested in variables that predict group membership or discriminate between groups Group membership becomes the dependent variable and the metric variables are considered independent variables MANOVA vs Multiple ANOVA s The critical issue distinguishing the two should be conceptual If you are interested in the dependent variables as a group MANOVA is probably preferable If the dependent variables do not hang together either conceptually or statistically then multiple univariate ANOVA s is probably preferable The two are not mutually exclusive If the multivariate null hypothesis is rejected then generally at least one of the univariate t s will be significant However this is not always the case Post hoc and planned comparisons may also be conducted in conjunction with MANOVA
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'