STP 231 Lecture Notes - Lecture 26: Data Point
Document Summary
Chapter 12: notes about regression line (mean of x, mean of y) lies on the fitted line. Assumed that data points are more or less in a line, if in a curve or no trend is apparent, avoid linear regression. We can make predictions by using the equation of the regression line: extrapolation. Predictions for values of the predictor variable outside the range of the observed values of the predictor value: outlier. Data point that is far off from the trend of the data points: influential observation. A data point, which when removed has a big impact on the data. Usually separated in the x direction from other data points. Pulls the regression line towards itself: important sums of squares. 3 summations that are important in assessment of the fit of regression lines. Gives total variability in y values unexplained. Gives total variability in y values explained by the regression equation.