Ch12.1 Simple Linear Regression The Simple Linear Regression Model There exists parameters 0 , 1 and 2 such that for any fixed.
Download ReportTranscript Ch12.1 Simple Linear Regression The Simple Linear Regression Model There exists parameters 0 , 1 and 2 such that for any fixed.
Ch12.1 Simple Linear Regression The Simple Linear Regression Model There exists parameters 0 , 1 and 2 such that for any fixed value of x, the dependent variable is related to x through the model equation y 0 1x ε is a random variable (called the random deviation) with E(ε) = 0 and V(ε) = σ2 One can see how a dependent variable is related to an independent variable with a scatter plot. Ch12.1 Ch12.1 Estimating Model Parameters Principle of Least Squares The vertical deviation of the point (xi,yi) from the line y = b0 + b1x is yi – (b0 + b1xi) The sum of squared vertical deviations from the points ( x1 , y1 ), ( x2 , y2 ),..., ( xn , yn )to the line is: n f (b0 , b1 ) yi b0 b1xi i 1 Ch12.2 2 The error sum of squares, denoted SSE, is SSE= yi yˆi 2 yi ˆ0 ˆ1 xi 2 and the estimate of σ2 is SSE ˆ s n2 2 2 yi yˆi 2 n2 A computational formula for the SSE, is SSE= yi2 ˆ0 yi ˆ1 xi yi The total sum of squares, denoted SST, is SST S yy yi y 2 2 yi yi / n 2 The coefficient of determination, denoted by r2, is given by SSE r 1 SST 2 Ch12.2 The least-squares (regression) line for the data is given by y ˆ0 ˆ1x where b1 ˆ1 x y x y / n x x / n i i i 2 2 i i and b0 ˆ0 i ˆ x y i 1i n y ˆ1 x ˆ1,..., y ˆ n are obtained by The fitted (predicted) values y substituting x1,..., xn into the equation of the estimated regression line: yˆ1 ˆ0 ˆ1x1,..., yˆn ˆ0 ˆ1xn . The residuals are the vertical deviations y1 yˆ1,..., yn yˆn from the estimated line. Ch12.2