Summary and study notes

Welke onderwerpen worden behandeld in het hoorcollege?

MANOVA = multivariate version of a basic ANOVA. Factor is independent variable that is categorical. Outcome is dependent variable that is continuous. An ANOVA has one outcome variable and a MANOVA has more outcome variables. With MANOVA, with one test, two or more groups are compared on multiple dependent variables simultaneously. 

Contrast testing = alternative to post-hoc comparisons. This are planned comparisons, therefore you don't need alpha corrections. 

Welke onderwerpen worden besproken die niet worden behandeld in de literatuur?

In dit college worden geen andere onderwerpen besproken dit niet worden behandeld in de literatuur.  

Welke recente ontwikkelingen in het vakgebied worden besproken? 

Er worden geen recente ontwikkelingen besproken. 

Welke opmerkingen worden er tijdens het college gedaan door de docent met betrekking tot het tentamen?

Er worden geen opmerkingen gedaan die betrekking hebben tot het tentamen. 

Welke vragen worden behandeld die gesteld kunnen worden op het tentamen? 

Er worden geen tentamenvragen behandeld. 

Hoorcollege aantekeningen

MANOVA = multivariate version of a basic ANOVA. Factor is independent variable that is categorical. Outcome is dependent variable that is continuous. An ANOVA has one outcome variable and a MANOVA has more outcome variables. 2x3 ANOVA means there are 2 factors, one with 2 levels and one with 3 levels. Main effect is when you look at just one factor. Interaction effect is when you look at the relation between the two factors. 

• Interaction effect = the effect of one factor on the outcome is different for different levels of another factor. When the lines in a plot are not parallel, there is interaction. Moderation is interaction, but with moderation you call one factor the moderator. A significant interaction effect does not tell you the story of interest (which subgroups score higher/lower than others). Follow-up tests after a significant interaction are called simple (main) effects. 
• Simple main effects = effect of one factor within one level of the other factor. It’s called a simple effect because you only look at one level. SPSS requires syntax commands to execute simple main effects. When you have a 2x3 ANOVA you have 2+3 simple main effects tests. 
  • • Run the factorial analysis of variance and paste syntax
    • Add lines to syntax to request simple main effects

Other things you need to know about factorial ANOVA

Effect sizes for all effects are partial eta squared = how much variation is explained by the factors. Contrast testing as alternative to (explanatory) post-hoc pairwise comparisons. If an ANOVA is significant but it compares more than two means, you only know that the means are not the same. Post-hoc comparisons search after the analysis how the groups differ (this is an exploratory approach wherefor you need a type I correction). Better is to test only the pre-specified hypotheses. Therefore, you don’t need alpha corrections à more power. This are planned comparisons = contrast testing. Disadvantage compared to exploring everything: exploring can expose unexpected results that may be interesting for future research. 

Contrast testing

Provided in SPSS menu for main effect only. For the order E – A – B. When you have 3 levels, you have 2 contrasts.

Simple contrast = each group is compared to the first group.

• Contrast 1: A vs E                  C1 = A – E                H0: C1 = 0
• Contrast 2: B vs E                  C2 = B – E                H0: C2 = 0

Repeated contrast = each group except the first is compared to the previous group. 

• Contrast 1: A vs E                  C1 = A – E                H0: C1 = 0
• Contrast 2 B vs A                   C2 = B – A               H0: C2 = 0

MANOVA

 With MANOVA, with one test, two or more groups are compared on multiple dependent variables simultaneously. Advantages over using several ANOVA’s are:

• Revealing (multivariate) differenced not seen with several ANOVA’s
• Protection for inflated type I error rate (capitalization on chance)

A MANOVA can have two dependent variables but also more. A MANOVA looks at the combined differences of the outcome variables, where an ANOVA just compare one outcome variable. You need to do a follow up analysis to see how the groups differ. 

What you need to know and understand about MANOVA:

• Two reasons to use a MANOVA
• Performing MANOVA in SPSS and correctly interpret Wilk’s lambda and follow-up ANOVA tests
• Assumptions of MANOVA and how to check these