ARMS
HC1
- Simple linear regression: 1 outcome and 1 predictor
- Multiple linear regression: involves 1 outcome and multiple predictors
Relevance of a predictor (1)
1. The amount of variance explained (R2) i.e. the sizes of the residuals
2. The slope of the regression line (B1), als X 1 punt stijgt, wat gebeurt er dan met Y?
Multiple linear regression (MLR)
- All assumptions (FIND IN GRASPLE, WILL BE ON TEST)
, - The model: ^y=predicted, Y1=0bserved. Observed score = predicted score + residual
- Types of variables
Distinction between 4 measurement levels: nominal, ordinal (both categorical), interval,
ratio (quantitative or numerical)
MLR requires continiour outcome and continuous predictors
Categorical predictors can be included if changed to dummy variable (gender: male=1,
female=0 for example). (1 & 2 not allowed, only 0 and 1 is allowed
(dummycoding kan worden geoefend op grasple)
C. MLR and hierarchical MLR
Hierarchical MLR example:
Are social network factors (as measured by child support (X3) and spouse support (X4) improving the
prediction of Life Satisfaction, if the effect of age and years of education are already accounted for?
Model 1: alleen Age en years of education
Model 2: age, years of education met daarbij spouse support en child support