SDS 306 Lecture Notes - Lecture 18: Coefficient Of Determination
Document Summary
R2: the variation accounted for by the model. Indicates the proportion of variance in one variable: that is accounted for by the other variable, also referred to as shared variance. For example: the correlation between children"s and parents" neuroticism scores is . 25: r2 = (. 25)2 = . 0625 which tells us: That 6. 25% of the variance in children"s neuroticism scores. Can be accounted for by their parent"s scores. R2 provides us with a measure of how useful the regression line is as a prediction tool. If r2 is close to 1, then the regression line is useful. If r2 is close to 0, then the regression line is not useful. What close to means depends on who is using it: good practice: always report r2 and let the researcher decide. Generally, if we want a higher r2: we would try out a different predictor variable, or use additional predictor variables r versus r2.