Concepts Flashcards
One way ANOVA
See how much of the variability in the OV can be explained by the PV
Comparing variability between groups against the variability within groups
Interaction
The effect of core PV on the OV is different for different levels of moderator (moderated by another PV)
Can be difference in direction or size
Interaction: main effect PV on x-axis
Check direction of both lines
Main effect if same direction
Interaction: main effect moderator PV:
Check positioning of lines
If one line always above the other then main effect of moderator PV
Interaction: interaction effect
Check if lines are parallel
If they have different slopes there is an interaction effect
Factorial ANOVA
Examining how much of the variance in our data can be explained by our predictor variables
Full model relationship to individual PV relationship)
Normal regression
Examine how much of the data can be explained by the PVs
When both PV and OV are quantitative
Logistic regression
Aim is to predict how likely it is that an event will occur, that the OV is equal to 1 or how likely that OV is equal to 0
Using odds ratio
Logistic regression
High cutoff rate
LESS 1s MORE 0s
Prediction of extra 0s are not correct for probability of correct estimates for 0 decreases and for 1 increases
Logistic regression
Low cutoff rate
MORE 1s LESS 0s
Prediction of extra 1s are not correct for probability of correct estimates for 1s decrease and for 0s increase