Lecture21 - lecture 21 Linear Regression II lecture 21...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
lecture 21, Linear Regression II 1 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Outline 1 Standard Error 2 Testing the Significance of the Slope 3 Reading the Computer Output
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
lecture 21, Linear Regression II 2 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Review Simple linear regression model: y = β 0 + β 1 x + ε, ε is N ( 0 , σ 2 ) . ( y = μ y | x + ε, ε is N ( 0 , σ 2 ) , μ y | x = β 0 + β 1 x . b 0 , b 1 : point estimates of β 0 , β 1 Estimation/prediction equation: ˆ y = b 0 + b 1 x (1)
Background image of page 2
lecture 21, Linear Regression II 3 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Review, ctd The least squares line: the line that minimizes the sum of squared error (SSE) (i.e., sum of squared residuals) SSE = n X i = 1 ( y i - ˆ y i ) 2 , where ˆ y i = b 0 + b 1 x i Least squares point estimates of β 0 and β 1 : b 1 = SXY SXX := n i = 1 ( x i - ¯ x )( y i - ¯ y ) n i = 1 ( x i - ¯ x ) 2 , b 0 = ¯ y - b 1 ¯ x .
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
lecture 21, Linear Regression II 4 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Estimating a Mean Fuel Consumption The least squares estimates of β 0 , β 1 : b 0 = 15 . 84 and b 1 = - 0 . 1279 . The least squares line: ˆ y = 15 . 84 - 0 . 1279 x . What’s the mean fuel consumption when the temperature x = 40? We want to estimate μ y | x = 40 = β 0 + β 1 · 40 , A point estimate: ˆ y = = 10 . 72 .
Background image of page 4
lecture 21, Linear Regression II 5 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Predicting an Individual Fuel Consumption What’s the fuel consumption that you would predict when the temperature x = 40? The fuel consumption when the temperature x = 40 is y = β 0 + β 1 · 40 + ε We have seen that ˆ y = b 0 + b 1 · 40 is a point estimate of β 0 + β 1 · 40 How about ε ? By assumption, ε is a normal random variable with mean zero, so it is symmetric around 0, and it is reasonable to predict the error term ε to be Point prediction: ˆ y = 15 . 84 - 0 . 1279 · 40 + 0 = 10 . 72
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
lecture 21, Linear Regression II 6 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Point Estimation and Point Prediction
Background image of page 6
lecture 21, Linear Regression II 7 / 24 Standard Error Testing the Significance of the Slope Reading the Computer Output lecture 21, Linear Regression II Point Estimation and Point Prediction, ctd Experimental region is the range of the observed values of x Suppose that the least squares line is ˆ y = b 0 + b 1 x .
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 24

Lecture21 - lecture 21 Linear Regression II lecture 21...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online