STAT 301 Lecture Notes - Lecture 21: Simple Linear Regression, Linear Regression, Squared Deviations From The Mean
Document Summary
Of a response variable, using values of a predictor variable (and assessing the uncertainty in these predictions) Quantifying how much a response variable tends to change. And whether this amount exceeds what we"d expect just by chance. Quantifying how much of the variability in a response variable can be attributed to variability in a predictor variable. We are not assuming that the predictor variable causes changes in the response variable. The difference between an actual observed value of y and the predicted value of y at the observed value of x. Visually, this is the vertical distance between a data point and the lobf. The lobf has the very important property that it minimizes the sum of the squared residuals (sse) If we took any line other than the lobf and calculated its sse, it would be bigger than the sse we get from the lobf.