Chapter 16 - 1 School of Business and Economics SUNY...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

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

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

Unformatted text preview: 1 School of Business and Economics SUNY Plattsburgh Slide 1 Business Statistics II ECO 362: Sections A & B Chapter 16 Regression Analysis: Model Building Spring 2011 Dr. Kameli a Petrova Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 2 Regression Analysis: Model Building s Multiple Regression Approach to Analysis of Variance and Experimental Design s General Linear Model s Determining When to Add or Delete Variables s Variable Selection Procedures s Residual Analysis Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 3 s Linear models: models in which all parameters ( , 1 , . . . , p ) have exponents of one. General Linear Model s General linear model with p independent variables: = + + + + + L 1 1 2 2 p p y z z z s Each of the independent variables z is a function of x 1 , x 2 ,..., x k (the variables for which data have been collected). Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 4 General Linear Model y x = + + 1 1 y x = + + 1 1 s The simplest case is when z 1 = x 1 . We want to estimate y by using a straight-line relationship. s Simple first-order model with one predictor (independent) variable. Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 5 Modeling Curvilinear Relationships s Second-order model with one predictor variable: y x x = + + + 1 1 2 1 2 y x x = + + + 1 1 2 1 2 s To account for a curvilinear relationship we set z 1 = x 1 and z 2 = x 1 2 Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 6 Interaction y x x x x x x = + + + + + + 1 1 2 2 3 1 2 4 2 2 5 1 2 y x x x x x x = + + + + + + 1 1 2 2 3 1 2 4 2 2 5 1 2 s This type of effect is called interaction . s Variable z 5 = x 1 x 2 is added to account for the potential effects of the two variables acting together. s Second-order model with two predictor variables. 2 Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 7 Transformations Involving the Dependent Variable s Reciprocal transformation: use 1/ y as the dependent variable instead of y . s The non-constant variance can be corrected by transforming the dependent variable to a different scale. s Logarithmic transformations: using either the base-10 (common log) or the base e = 2.71828... (natural log). Log(y) or Ln(y) instead of y Spring 2011 Dr. Kameli a Petrova School of Business and Economics SUNY Plattsburgh Slide 8 s Transform to a linear model by taking the logarithm of both sides. E y x ( ) = 1 E y x ( ) = 1 Nonlinear Models That Are Intrinsically Linear s Models in which the parameters ( , 1 , . . . , p ) have exponents other than one are called nonlinear models ....
View Full Document

Page1 / 7

Chapter 16 - 1 School of Business and Economics SUNY...

This preview shows document pages 1 - 3. Sign up to view the full document.

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