4.10_linear_reg - Linear Regression 25 20 15 y 10 5 0-5 0 5...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Mike Pore - Sept 2004 Linear Regression 0 5 10 15 20 25 y -5 0 5 10 15 20 25 30 35 x Linear Fit
Background image of page 1

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

View Full DocumentRight Arrow Icon
2 Mike Pore - Sept 2004 Topics Scatterplots Correlation Least squares regression Residual plots Causation Tests of regression Transformations Probability intervals
Background image of page 2
3 Mike Pore - Sept 2004 Scatterplots In the beginning, we have paired variables: (x 1 , y 1 ), (x 2 , y 2 ), . . . , (x n , y n ) The Y are observations The X can be either observations or observer determined values of the X variable.
Background image of page 3

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

View Full DocumentRight Arrow Icon
4 Mike Pore - Sept 2004 Scatterplots 0 5 10 15 20 25 y -5 0 5 10 15 20 25 30 35 x
Background image of page 4
5 Mike Pore - Sept 2004 Modeling the Data with a Line 0 5 10 15 20 25 y -5 0 5 10 15 20 25 30 35 x Linear Fit
Background image of page 5

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

View Full DocumentRight Arrow Icon
6 Mike Pore - Sept 2004 Graphing a Line x y b x b b y = + = 1 1 0 x 1 x 2 y 1 y 2 (x 1 , y 1 ) (x 2 , y 2 ) (0, b 0 ) x y
Background image of page 6
7 Mike Pore - Sept 2004 Graphing a Line The slope: b 1 0 5 10 15 20 x Positive: up to the right Y=x has slope 1 Slope 2 is half way from 1 to vertical Slope 4 is half way from 2 to vertical Slope ½ is half way from 1 to horizonal Slope 1/4 is half way from ½ to horizonal Negative: down to the right Y=-x has slope -1 Slope -2 is half way from -1 to vertical Slope -4 is half way from -2 to vertical Slope -½ is half way from -1 to horizonal Slope -1/4 is half way from -½ to horizonal Zero: horizonal
Background image of page 7

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

View Full DocumentRight Arrow Icon
8 Mike Pore - Sept 2004 Data Calculations i x i y i 1 2 n ( 29 x x i - ( 29 y y i - ( 29 2 x x i - ( 29 2 y y i - ( 29 ( 29 y y x x i i - - ( 29 ( 29 - - = - - = 2 2 1 1 1 1 y y n s x x n s i y i x - - - = y i x i s y y s x x n r n correlatio 1 1
Background image of page 8
9 Mike Pore - Sept 2004 Correlation
Background image of page 9

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

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 38

4.10_linear_reg - Linear Regression 25 20 15 y 10 5 0-5 0 5...

This preview shows document pages 1 - 10. Sign up to view the full document.

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