4-27-2011 Homoscedasticity

4-27-2011 Homoscedasticity - 4/27/2011 Lecture 25: April...

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

View Full Document Right Arrow Icon
•4/27/2011 •1 Lecture 25: April 27, 2011 • Discussion this Friday: – Overall significance of a regression equation – Prediction interval for an individual Y – Identifying heteroscedasticity and autocorrelation – Multiple regression • Final Exam: – Thursday, May 5: 8:00 a.m., Boyden Gym • Topics for the final exam: – Everything I covered after Exam 2 – I’ll have detailed pages on Monday. • Review sessions (Tentative until rooms are confirmed): – Friday, April 29, 3:30 p.m., Stockbridge 124 – Wednesday, May 4, 3:30 p.m., Thompson 104 • Last Connect activities – Homework No. 13 and Quiz No. 5 – Each will be ready Thursday evening and due next Wednesday. Note: Here are the kinds of questions you will be asked in Homework No. 13 and Quiz No. 5. • You will be given a familiar section of the regression output and asked any of the following: – to fill in a blank – for an interpretation of a number – to do a calculation • To do this successfully, you must: – be familiar with all vocabulary items – know how a vocabulary item is calculated • We will be doing all of this today. I am finished with Chapter 12. • Let’s move to Chapter 13. • Multiple regression. • It is an extension of bivariate regression.
Background image of page 1

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

View Full DocumentRight Arrow Icon
•4/27/2011 •2 The simple regression model from the previous three classes • I will put a “1” subscript on the “X” variable. • Reason: There is only one independent variable in this simple model. • This is called a bivariate regression model. – “bi” “variate” two variables Y and X 1 • Is there any reason to have only one independent variable? • The model could be •o r 01 Y= X+  1 Y= X  1 2 2 Y= X + X  1 2 23 3 Y= X + X X   A more general regression model • If there are “k” variables, in general, the model is: • This is Equation (13.1) on page 545 of the text. • This is no longer a bivariate regression model. • Since there are multiple variables, this is called a multiple regression model. • It has “k” predictor variables or independent variables (in addition to an intercept). • So, the model has “k+1” parameters. • Let’s look closely at the components of this model. 1 2 2 k k Y= X + X ... X   Model: Y is the response variable or dependent variable. X 1 , X 2 , …, X k are independent variables or predictor variables or covariates. β 0 , β 1 , β 2 , …, β k are unknown population parameters.
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/13/2011 for the course FINOPMGT 250 taught by Professor Kouzehkanani during the Spring '08 term at UMass (Amherst).

Page1 / 8

4-27-2011 Homoscedasticity - 4/27/2011 Lecture 25: April...

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