PDB_Stat_100_Lecture_27_Printable

PDB_Stat_100_Lecture_27_Printable - STA 100 Lecture 27 Paul...

Info iconThis preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon
STA 100 Lecture 27 Paul Baines Department of Statistics University of California, Davis March 11th, 2011
Background image of page 1

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

View Full DocumentRight Arrow Icon
Admin for the Day I Final project due today, 3pm I Office hours Friday – 9.30-11.30am I Practice Final Exam Questions Posted I Review session on Monday References for Today: Rosner, Ch 11, Ch 12 (7th Ed.) References for Friday: Rosner, Ch 11, Ch 12 (7th Ed.)
Background image of page 2
Understanding R 2 We can decompose the total variability in our data: n X i =1 ( y i - ¯ y ) 2 = n X i =1 y i - ¯ y ) 2 + n X i =1 ( y i - ˆ y i ) 2 Total SS = Regression SS + Residual SS Using this, it turns out that R 2 also has a nice interpretation: R 2 = r 2 = n i =1 y i - ¯ y ) 2 n i =1 ( y i - ¯ y ) 2 = Regression SS Total SS
Background image of page 3

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

View Full DocumentRight Arrow Icon
Understanding R 2 Using this definition, we get a nice interpretation for R 2 as: the proportion of variability in y that can be explained by a linear relationship with x . Sometimes we use a slightly modified version of R 2 , known as adjusted R 2 . Details will be omitted, but you should use adjusted R 2 (with the same interpretation as above).
Background image of page 4
10 11 12 13 2 4 6 8 Histogram of y y
Background image of page 5

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

View Full DocumentRight Arrow Icon
10.00 10.05 10.10 10.15 10.20 10.25 10.30 Total Variability in the Response Variable (Zoom In) Response Variable (y) Mean of y y 1 y 2 y 3 y 4 y 5 y 1 - y y 2 - y y 3 - y y 4 - y y 5 - y
Background image of page 6
2 4 6 8 10 9.0 9.5 10.0 10.5 11.0 Total Variability in the Response Variable (Zoom In) Explanatory Variable (x) Response Variable (y) ( x 1 , y 1 29 ( x 2 , y 2 29 ( x 3 , y 3 29 ( x 4 , y 4 29 ( x 5 , y 5 29
Background image of page 7

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

View Full DocumentRight Arrow Icon
2 4 6 8 10 9.0 9.5 10.0 10.5 11.0 Residual Variability in the Response After Regression (Zoom In) Explanatory Variable (x) Response Variable (y) ( x 1 , y 1 29 ( x 2 , y 2 29 ( x 3 , y 3 29 ( x 4 , y 4 29 ( x 5 , y 5 29
Background image of page 8
2 4 6 8 10 9.0 9.5 10.0 10.5 11.0 Regression Variability in the Response (Zoom In) Explanatory Variable (x) Response Variable (y) ( x 1 , y 1 29 ( x 2 , y 2 29 ( x 3 , y 3 29 ( x 4 , y 4 29 ( x 5 , y 5 29
Background image of page 9

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

View Full DocumentRight Arrow Icon
2 4 6 8 10 9.0 9.5 10.0 10.5 11.0 Decomposing Variability in the Response (Zoom In) Explanatory Variable (x) Response Variable (y) ( x 1 , y 1 29 ( x 2 , y 2 29 ( x 3 , y 3 29 ( x 4 , y 4 29 ( x 5 , y 5 29
Background image of page 10
Interpreting R 2 Heuristically, we interpret this decomposition as: (Total Variability of Response Variable) = (Variability of Points on the Regression Line) + (Variability of Points around Regression Line) Or, put another way: (Variation ignoring the explanatory variable) = (Variation explained by the linear relationship) + (Variation not explained by the linear relationship) Thus: R 2 = ± Variation in Response Variable Explained by the Linear Relationship with the Explanatory Variable ² Total Variation in Response Variable
Background image of page 11

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

View Full DocumentRight Arrow Icon
Doing Linear Regression For the brain-body weight example we get: > RegModel.2 <- lm(log(brain)~log(body), data=animals) > summary(RegModel.2) ... Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 2.99064 0.47051 6.356 1.18e-06 *** log(body) 0.43580 0.08751 4.980 3.93e-05 *** --- Signif. codes: 0 ’***’ 0.001 ’**’ 0.01 ’*’ 0.05 ’.’ 0.1 ’ ’ 1 Residual standard error: 1.655 on 25 degrees of freedom Multiple R-squared: 0.498, Adjusted R-squared: 0.4779 F-statistic: 24.8 on 1 and 25 DF, p-value: 3.926e-05 Therefore, 49.8% of the variability in log-brain weight can be explained by the linear relationship with log-body weight.
Background image of page 12
Image of page 13
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/17/2012 for the course STAT 100 taught by Professor drake during the Fall '10 term at UC Davis.

Page1 / 39

PDB_Stat_100_Lecture_27_Printable - STA 100 Lecture 27 Paul...

This preview shows document pages 1 - 13. Sign up to view the full document.

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