spring2013stat202-lecture08

# spring2013stat202-lecture08 - Lecture 8 Fri Feb 1 36-202...

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

Lecture 8 36-202 Fri, Feb. 1 Spring 2013 This document is available on: (under ‘course content’) Continuing Multiple Linear Regression [Reserve Material References: Chapter 13 of Statistics By Agresti and Franklin; Chapter 11 of Introduction to the Practice of Statistics by Moore, McCabe; Chapter 30 of Stats: Data and Models by Deveaux et al] In the previous lecture, we introduced the Multiple Linear Regression Model: The Multiple Linear Regression Model A model of the relationship in the population between a response variable Y and p -many explanatory (‘predictor’) variables X 1 , X 2 , … , X p . The Multiple Linear Regression Model proposes that the observed response is given by: y i = β 0 + β 1 x 1 i + β 2 x 2 i + . . . + β p x pi + ε i where the errors ε i are (as in the simple linear regression model) assumed to be: independent, and: Normally distributed with mean 0 and constant (for all x ) standard deviation σ [i.e., ε i ~ N(0, σ ) ] This model has p +2 parameters: β 0 , β 1 , β 2 , . . . β p , and σ , such that: (a) (b) Each β j is the (average population) change in the response Y when X j increases by 1 unit and all the other explanatory variables remain fixed (unchanging); σ is, as in the simple linear regression model, the typical deviation of the population Y values from the regression function. The ‘steps’ involved in the multiple linear regression model are similar to those involved in the simple linear regression model, but with the addition of a new EDA tool, the correlation matrix [note that software shows the results of several of these steps together]: State the model; Obtain data from one sample; Perform EDA on the data: o Scatterplots of Y vs. each separate X o The correlation matrix Use the Least Squares method to estimate the β j s from the data, and then use those estimates to construct the regression equation; Use the regression equation to compute the residuals, and then: o use the residuals to estimate σ ; o use a residual plot (and a Normal probability plot) to check the assumptions of the model; Conduct tests of significance of the relationship; Use R 2 to measure the effectiveness of the model for predicting y

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

View Full Document
Statistics Lecture 8 Page 2 of 10 This document is available on: (under ‘course content’) Example (continued from last time): Middle-school GPA Data was collected from 71 seventh-grade students in rural Midwestern school.* The researcher was interested in examining how much of the variability in the students’ GPA can be explained by their IQ level and their “self concept.”
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern