week6_lec1-2_regression_s09hdd-1

week6_lec1-2_regression_s09hdd-1 - Get Fired-Up! l Start l...

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

View Full Document Right Arrow Icon
Get Fired-Up!! l Start one computer per pair l Get on Blackboard l Go to: Lecture Slides, Prof. Diefes-Dux Folder l Save: regression_examples_diefes-dux.xlsx to desktop or H: drive l Start Excel – open saved file l Start MATLAB
Background image of page 1

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

View Full DocumentRight Arrow Icon
Due Today l MEA 1 Peer Critique (Due Today 2/17) Reminder: It is critical that you complete all parts of the MEA 1 sequence. Failure to complete any part will lock you out of the rest of the sequence and could result in a grade of zero on MEA 1. l Regression with Linear Scales l Notes pp. 78-84 l Textbook Ch 12 pp. 444-446; 448-449
Background image of page 2
Checking for Understanding… ? 5 1 = = i i (not in notes)
Background image of page 3

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

View Full DocumentRight Arrow Icon
Plotting and Regression with Linear Scales Learning Objectives (Notes: 78-84) At the end of this class period, you will begin to be able to: l State why we do regression l Produce the equation of a regression line l Manually l Using MATLAB l Using Excel l Define, calculate, and explain the use of l SSE sum of the squares of errors l SST sum of the squares of deviations l r2 coefficient of determination
Background image of page 4
A regression is a method of creating a model of a system l Paired data sets l We’ve measured both X and Y l We think that Y may depend on X l So first we plot the data X Y The line is potentially a MODEL of the data. Is it a GOOD model?
Background image of page 5

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

View Full DocumentRight Arrow Icon
When using regression, we assume that one variable is a function of another l Cause-and-Effect l Distance is a function of launch angle l Reaction rate is a function of temperature l Changes over Time (temporal changes) l Coffee (in cup) temperature is function of time l Gross Domestic Product (GDP) is a function of time l Spatial Profile l The number of pedestrians crossing the street is a function of location along the street
Background image of page 6
You probably learned in mathematics that functions can be represented four ways l Verbally : describe the relationship l Numerically : tabulate the data l Visually : show us a graph l Symbolically : use an equation as a model Today, we’ll focus on the last two: l Visually: Fit a “best” regression line to graphed data l Symbolically: Find the “best” regression line equation
Background image of page 7

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

View Full DocumentRight Arrow Icon
What is a linear regression analysis? Given a set of data, develop a line y = a x + b where: l (x,y) represents the raw data points l a is the slope (change in y over change in x ) l b is the y -intercept when x = 0 that “best fits” data How do we determine a and b? How do we determine what is the “best” fit?
Background image of page 8
Telephone Expenditures (1981-1999) y = a x + b where: l (x,y) represents the raw data points of year l x for annum l y for phone expenditures l a is the slope of the line in phone cost/year l b is the intercept, which doesn't mean much here, since it's the phone cost in 0 A.D. Best Fit Line Raw Data Notes p. 79
Background image of page 9

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

View Full DocumentRight Arrow Icon
Two-Point Method to Determine Slope and Intercept Point 1 (1981,360) and Point 2 (1999,849) b = C – m A = 360 – 27.17(1981) = -53464 Our equation for the line through the first and last points is: y = 27.17 x - 53464 2 1 2 1 849 360 27.17 1999 1981 y y m x x - - = = = - -
Background image of page 10
Two-Point Method to Determine Slope and Intercept Alternatively, compute b using both points Solve simultaneously for b Our equation for the line through the first and last points is
Background image of page 11

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

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

This note was uploaded on 03/06/2011 for the course ENGR 126 taught by Professor Oakes during the Spring '08 term at Purdue University-West Lafayette.

Page1 / 48

week6_lec1-2_regression_s09hdd-1 - Get Fired-Up! l Start l...

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