Lecture 6 - 6.2142857*4 =-10.7142858 Thus the regression...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon
Relationships can be deceiving An outlier is defined to be any value that is more than 1.5*IQR beyond the closest quartile. A value is an outlier if either 1) the value is greater than Q 3 +(1.5*IQR) 2) the value is less than Q 1 -(1.5*IQR) Ex. What is the possible outlier? X: 2 5 7 9 10 11 55 Q 1 = P 25 =(n*k)th # Q 3 = P 75 =(n*k)th #
Background image of page 1

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

View Full DocumentRight Arrow Icon
IQR = A value is an outlier if either 1) the value is greater than 2) the value is less than
Background image of page 2
How does an outlier effect the correlation? X: 1 2 3 4 5 6 7 Y: 2 5 7 9 10 11 55 x y 7 6 5 4 3 2 1 60 50 40 30 20 10 0 Scatterplot of y vs x
Background image of page 3

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

View Full DocumentRight Arrow Icon
Find the correlation X Y X 2 Y 2 XY 1 2 1 4 2 2 5 4 25 10 3 7 9 49 21 4 9 16 81 36 5 10 25 100 50 6 11 36 121 66 7 55 49 3025 385 x= y= x 2 = y 2 xy
Background image of page 4
Background image of page 5

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

View Full DocumentRight Arrow Icon
Now drop the outlier we found earlier and find the correlation. X Y X 2 Y 2 XY 1 2 1 4 2 2 5 4 25 10 3 7 9 49 21 4 9 16 81 36 5 10 25 100 50 6 11 36 121 66 x= y x 2 y 2 xy
Background image of page 6
Background image of page 7

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

View Full DocumentRight Arrow Icon
How does an outlier effect the correlation? Using the same values and the Sum of Squares form the previous examples X: 1 2 3 4 5 6 7 Y: 2 5 7 9 10 11 55 For all the original 7 pairs of points X = x n = 28/7 = 4 Y = y n = 99/7 = 14.142857 b = SSxy/SSxx = 174/28 = 6.2142857 a = Y - b* X = 14.142857 –
Background image of page 8
Background image of page 9

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

View Full DocumentRight Arrow Icon
Background image of page 10
Background image of page 11

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

View Full DocumentRight Arrow Icon
Background image of page 12
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 6.2142857*4 = -10.7142858 Thus, the regression line for the original 7 pairs is ˆ y = 6.2142857*x - 10.7142858 x y 7 6 5 4 3 2 1 60 50 40 30 20 10 Scatterplot of y vs x Now drop the outlier we found earlier and find the correlation. So, we are only working with 6 pairs of numbers. X = x n ∑ = 21/6 = 3.5 Y = y n ∑ = 44/6 = 7.333333333 b = SSxy/SSxx = 31/17.5 = 1.771428571 a = Y- b* X = 7.33333333– 1.771428571*3.5 = 1.13333333 Thus, the regression line for the 6 pairs after the outlier is dropped. ˆ y = 1.771428571*x + 1.133333333 x_1 y_1 6 5 4 3 2 1 12 10 8 6 4 2 Scatterplot of y_1 vs x_1 Now look at the two regression lines superimposed on the same graph X-Data Y-Data 7 6 5 4 3 2 1 60 50 40 30 20 10 Variable y * x y_1 * x_1 Scatterplot of y vs x, y_1 vs x_1 The outlier pulls the regression line towards it....
View Full Document

This note was uploaded on 02/15/2009 for the course STAT 2004 taught by Professor Melutz during the Fall '07 term at Virginia Tech.

Page1 / 12

Lecture 6 - 6.2142857*4 =-10.7142858 Thus the regression...

This preview shows document pages 1 - 12. Sign up to view the full document.

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