EC285 Chapter Notes - Chapter 6: Standard Deviation, Linear Regression, Scatter Plot
Document Summary
Scatterplots tell us qualitative information about the relationship of two variables: Weak or strong relationship: if the scatterplot is in a single stream then the relationship is strong. Explanatory or predictor variable goes on the x-axis and the response variable is the y-axis. Also known as dependent (y) and independent (x) variables. Covariance measures what extent two variables move together. If covariance > 0, x and y tend to move in the same direction. If covariance < 0, x and y tend to move in the opposite direction. If covariance = 0, there is no linear relationship. Sample covariance: (cid:1841)(cid:4666)(cid:1876),(cid:1877)(cid:4667)=(cid:3051)(cid:3052)= (cid:4666)(cid:1876) (cid:3051)(cid:4667)(cid:4666)(cid:1877) (cid:3052)(cid:4667) (cid:1840) (cid:1855)(cid:1867)(cid:4666)(cid:1876),(cid:1877)(cid:4667)=(cid:1871)(cid:3051)(cid:3052)= (cid:4666)(cid:1876) (cid:1876) (cid:4667)(cid:4666)(cid:1877) (cid:1877) (cid:4667) (cid:1866) (cid:883) The further x and y are away from their mean, the greater the magnitude (absolute value) of. Covariance doesn"t measure the strength of the relationship and changes when unit of measurement changes. The correlation coefficient measures the strength of a relation: