ChE253K Spring09 Lecture07.Rev06

# ChE253K Spring09 Lecture07.Rev06 - Class Business HW01 Back...

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

1 UT ChE 253K Lecture 07 Class Business HW01 Back HW02 Due HW03 Posted

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

View Full Document
2 UT ChE 253K Lecture 07 How To Fit Data Using Linear Regression Lecture 07 -- Descriptive Statistics
3 UT ChE 253K Lecture 07 What To Learn And Why How to calculate a linear regression line

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

View Full Document
4 UT ChE 253K Lecture 07 Objective Of Linear Regression A reasonable line Ŷ = a + bX Ŷ(i) = a + b(C(i)) that minimizes the deviations or residuals e(i) = Y(i) - Ŷ(i) between measured Y(i) and the line’s Ŷ(i) Sources: Miller & Freund text
5 UT ChE 253K Lecture 07 Least Squares Linear Regression Sources: www-micro.lsb.le.ac.uk

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

View Full Document
6 UT ChE 253K Lecture 07 Linear Reg’n Optimization Prob’m Objective function to minimize Sum squared residuals (SSE) Least-squares linear reg’n Sum signed residuals Canceling Unreasonable Sum absolute residuals “Robust regression” 1 ( ) n i i i Y a bX = - + 1 [ ( )] n i i i Y a bX = - + 2 1 [ ( )] n i i i Y a bX = - +
7 UT ChE 253K Lecture 07 Minimization Procedure & Result Find a & b to minimize SSE find the zero’s of the partial derivatives After some algebra (given in the Text) ( 29 2 1 [ ( )] 0 n i i i SSE Y a bX a a = = - + = ( 29 b SSE =0 a Y bX = - xy xx b S S = ˆ ˆ ( ) ( ) Y Y bX bx Y Y b X X = - + - = -

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

View Full Document
8 UT ChE 253K Lecture 07 S xy S yy S xx 5.4 2 Mean 17.00 29.20 10 0 0 27 10 Sum 4 3.6 2 9 4 1.60 2.56 1 1.6 1 7 3 0.00 0.16 0 -0.4 0 5 2 1.40 1.96 1 -1.4 -1 1 6.80 11.56 4 -3.4 -2 2 Tools For Regression Calculations Sources: Means X = ____ Y = ____ N = ____ Sums of Squares Sxx = ____ Syy = ____ Sxy = ____ Slope, Intercept, CofD a = ____ b = ____ r 2 = ____ StdError, α , ν , t s e = ____ α = ____ ν = ___ t = ____ Confidence Intervals a ± ____ b ± ____ 0 2 4 6 8 10 0 1 2 3 4 5 Additive, qty Life, hrs 1 1 1 1 1 ( )( ) n n n n xy i i i i i i i i i i S X X Y Y X Y X Y n = = = =  - - = -  
9 UT ChE 253K Lecture 07 Data Scatter Plot. Linear? Additive Life, hrs 0 2 1 4 2 5 3 7 4 9 0 2 4 6 8 10 0 1 2 3 4 5 Additive, qty Life, hrs Sources: Text Exercise 11.2

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

View Full Document
10 UT ChE 253K Lecture 07 Data Scatter Plot. Linear! Additive Life, hrs 0 2 1 4 2 5 3 7 4 9 0 2 4 6 8 10 0 1 2 3 4 5 Additive, qty Life, hrs Sources: Text Exercise 11.2
11 UT ChE 253K Lecture 07 Sums of Squares: S xx , S yy , S xy Deviation of X from its mean Deviation of Y from its mean Cross-product of X & Y deviations 2 2 2 1 1 1 1 ( ) n n n xx i i i i i i S X X X X n = = = - = - 1 1 1 1 1 ( )( ) n n n n xy i i i i i i i i i i S X X Y Y X Y X Y n = = = =  - - = -   2 2 2 1 1 1 1 ( ) n n n yy i i i i i i S Y Y Y Y n = = = - = -

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

View Full Document
12 UT ChE 253K Lecture 07 Sums of Squares Co/Variance Deviation of X from its mean
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 02/25/2010 for the course CHE 253k taught by Professor Staff during the Spring '08 term at University of Texas at Austin.

### Page1 / 43

ChE253K Spring09 Lecture07.Rev06 - Class Business HW01 Back...

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

View Full Document
Ask a homework question - tutors are online