1 1 Chapter 5: Multiple Regression 5.1 Fitting a Multiple Regression Model 5.2 Fitting a Multiple Regression Model with Interactions 5.3 Generating and.

Slides:



Advertisements
Similar presentations
Copyright © 2009 Pearson Education, Inc. Chapter 29 Multiple Regression.
Advertisements

Inference for Regression
Some Terms Y =  o +  1 X Regression of Y on X Regress Y on X X called independent variable or predictor variable or covariate or factor Which factors.
Chapter 13 Multiple Regression
LINEAR REGRESSION: Evaluating Regression Models Overview Assumptions for Linear Regression Evaluating a Regression Model.
LINEAR REGRESSION: Evaluating Regression Models. Overview Assumptions for Linear Regression Evaluating a Regression Model.
Copyright © 2010, 2007, 2004 Pearson Education, Inc. *Chapter 29 Multiple Regression.
Chapter 10 Simple Regression.
1 Chapter 3 Multiple Linear Regression Ray-Bing Chen Institute of Statistics National University of Kaohsiung.
Statistics 350 Lecture 16. Today Last Day: Introduction to Multiple Linear Regression Model Today: More Chapter 6.
Lecture 22 Multiple Regression (Sections )
Multivariate Data Analysis Chapter 4 – Multiple Regression.
CHAPTER 4 ECONOMETRICS x x x x x Multiple Regression = more than one explanatory variable Independent variables are X 2 and X 3. Y i = B 1 + B 2 X 2i +
Chapter 11 Multiple Regression.
Lecture 23 Multiple Regression (Sections )
Multiple Regression and Correlation Analysis
Ch. 14: The Multiple Regression Model building
Measures of Association Deepak Khazanchi Chapter 18.
Multiple Regression Research Methods and Statistics.
Simple Linear Regression Analysis
Statistical hypothesis testing – Inferential statistics II. Testing for associations.
McGraw-Hill/IrwinCopyright © 2009 by The McGraw-Hill Companies, Inc. All Rights Reserved. Simple Linear Regression Analysis Chapter 13.
Chapter 13: Inference in Regression
Chapter 11 Simple Regression
Chapter 14 Introduction to Multiple Regression Sections 1, 2, 3, 4, 6.
Inferences in Regression and Correlation Analysis Ayona Chatterjee Spring 2008 Math 4803/5803.
OPIM 303-Lecture #8 Jose M. Cruz Assistant Professor.
Copyright © 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Slide
Multiple regression - Inference for multiple regression - A case study IPS chapters 11.1 and 11.2 © 2006 W.H. Freeman and Company.
Multiple Linear Regression. Purpose To analyze the relationship between a single dependent variable and several independent variables.
Multiple Regression and Model Building Chapter 15 Copyright © 2014 by The McGraw-Hill Companies, Inc. All rights reserved.McGraw-Hill/Irwin.
Inference for Regression Simple Linear Regression IPS Chapter 10.1 © 2009 W.H. Freeman and Company.
Multiple Regression Petter Mostad Review: Simple linear regression We define a model where are independent (normally distributed) with equal.
11 Chapter 12 Quantitative Data Analysis: Hypothesis Testing © 2009 John Wiley & Sons Ltd.
CORRELATION: Correlation analysis Correlation analysis is used to measure the strength of association (linear relationship) between two quantitative variables.
Chapter 16 Data Analysis: Testing for Associations.
Simple Linear Regression (SLR)
Simple Linear Regression (OLS). Types of Correlation Positive correlationNegative correlationNo correlation.
Data Analysis.
ECON 338/ENVR 305 CLICKER QUESTIONS Statistics – Question Set #8 (from Chapter 10)
Multiple Regression. Simple Regression in detail Y i = β o + β 1 x i + ε i Where Y => Dependent variable X => Independent variable β o => Model parameter.
© 2006 by The McGraw-Hill Companies, Inc. All rights reserved. 1 Chapter 12 Testing for Relationships Tests of linear relationships –Correlation 2 continuous.
General Linear Model.
Psychology 202a Advanced Psychological Statistics November 12, 2015.
Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Simple Linear Regression Analysis Chapter 13.
Chapter 11: Linear Regression and Correlation Regression analysis is a statistical tool that utilizes the relation between two or more quantitative variables.
1 Introduction to Modeling Beyond the Basics (Chapter 7)
Research Methodology Lecture No :26 (Hypothesis Testing – Relationship)
Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Multiple Regression Chapter 14.
Construction Engineering 221 Probability and Statistics.
Copyright © 2008 by Nelson, a division of Thomson Canada Limited Chapter 18 Part 5 Analysis and Interpretation of Data DIFFERENCES BETWEEN GROUPS AND RELATIONSHIPS.
Lecturer: Ing. Martina Hanová, PhD.. Regression analysis Regression analysis is a tool for analyzing relationships between financial variables:  Identify.
Multiple Regression Reference: Chapter 18 of Statistics for Management and Economics, 7 th Edition, Gerald Keller. 1.
INTRODUCTION TO MULTIPLE REGRESSION MULTIPLE REGRESSION MODEL 11.2 MULTIPLE COEFFICIENT OF DETERMINATION 11.3 MODEL ASSUMPTIONS 11.4 TEST OF SIGNIFICANCE.
Chapter 11: Linear Regression E370, Spring From Simple Regression to Multiple Regression.
Predicting Energy Consumption in Buildings using Multiple Linear Regression Introduction Linear regression is used to model energy consumption in buildings.
Chapter 20 Linear and Multiple Regression
ANOVA (Chapter - 04/D) Dr. C. Ertuna.
STA 282 Introduction to Statistics
BIVARIATE REGRESSION AND CORRELATION
Correlation and Simple Linear Regression
CHAPTER 29: Multiple Regression*
Prepared by Lee Revere and John Large
DRQ 8 Dr. Capps AGEC points
Correlation and Simple Linear Regression
Simple Linear Regression and Correlation
Essentials of Statistics for Business and Economics (8e)
Nazmus Saquib, PhD Head of Research Sulaiman AlRajhi Colleges
Correlation and Simple Linear Regression
Correlation and Simple Linear Regression
Presentation transcript:

1 1 Chapter 5: Multiple Regression 5.1 Fitting a Multiple Regression Model 5.2 Fitting a Multiple Regression Model with Interactions 5.3 Generating and Comparing Candidate Models

2 2 Chapter 5: Multiple Regression 5.1 Fitting a Multiple Regression Model 5.2 Fitting a Multiple Regression Model with Interactions 5.3 Generating and Comparing Candidate Models

3 Objectives Understand the principles of multiple linear regression. Recognize the main advantage of multiple regression versus simple linear regression. Fit a multiple regression model with the Fit Model platform. 3

4 Multiple Linear Regression Model In general, the dependent variable Y is modeled as a linear function of k independent variables (the Xs): Y =  0 +  1 X 1 + … +  k X k +  Consider the model where k = 2: Y =  0 +  1 X 1 +  2 X 2 +  4

5 Picturing the Model: No Relationship 5

6 Picturing the Model: A Relationship 6

7 Model Hypothesis Test Null Hypothesis: The regression model does not fit the data better than the baseline model. H 0 :  1 =  2 = … =  k = 0 Alternative Hypothesis: The regression model does fit the data better than the baseline model. H 1 : Not all  s equal zero. 7

Multiple Choice Poll Which statistic in the ANOVA table tests the overall hypothesis? a. F b. t c. R 2 d. Adjusted R 2 8

Multiple Choice Poll – Correct Answer Which statistic in the ANOVA table tests the overall hypothesis? a. F b. t c. R 2 d. Adjusted R 2 9

10 Assumptions for Linear Regression The variables are related linearly. The errors are normally distributed with a mean of zero. The errors have a constant variance. The errors are independent. 10

11 Multiple Linear Regression versus Simple Linear Regression Main Advantage Multiple linear regression enables an investigation of the relationship between Y and several independent variables simultaneously. Main Disadvantages Increased complexity makes it more difficult to ascertain which model is best interpret the models. 11

12 Common Applications Multiple linear regression is a powerful tool for Prediction – to develop a model to predict future values of a response variable (Y) based on its relationships with other predictor variables (Xs) Analytical or Explanatory Analysis – to develop an understanding of the relationships between the response variable and predictor variables. 12

13 Prediction Sometimes the terms in the model, the values of their coefficients, and their statistical significance are of secondary importance. The focus is on producing a model that is the best at predicting future values of Y as a function of the Xs. The predicted value of Y is given by 13 Y = β 0 + β 1 X 1 + … + β k X k

14 Analytical or Explanatory Analysis Sometimes the focus is on understanding the relationship between the dependent variable and the independent variables. Consequently, the statistical significance of the coefficients is important, as well as the magnitudes and signs of the coefficients. 14 …… ………

15 Fitness Example Simple Linear Regressions: Multiple Regression: 15 TermEstimatep-value Age Weight Runtime-3.31< Run Pulse Rest Pulse Maximum Pulse ?

16 This demonstration illustrates the concepts discussed previously. Fitting a Multiple Regression Model

17

18 Chapter 5: Multiple Regression 5.1 Fitting a Multiple Regression Model 5.2 Fitting a Multiple Regression Model with Interactions 5.3 Generating and Comparing Candidate Models

19 Objectives Add interactions to a multiple regression model. Fit a multiple regression model with interactions. 19

20 Interactions An interaction exists if the effect of one variable on the response depends on the level of another variable. 20

21 Stability Example A chemist is assessing the impact of acid concentration (A), catalyst concentration (C), temperature (T), and monomer concentration (M) on polymer stability. She is concerned that there might be two-factor interactions between some of the variables. Here is the full model: S = β 0 + β 1 A + β 2 C + β 3 T + β 4 M + β 5 A*C + β 6 A*T + β 7 A*M + β 8 C*T + β 9 C*M + β 10 T*M + ε 21

22 This demonstration illustrates the concepts discussed previously. Fitting a Multiple Regression Model with Interactions

Multiple Choice Poll The interaction term x1*x2 has a p-value of The p-value for x1 is 0.25 and the p-value for x2 is With a predetermined alpha of 0.05, what parameters should be included in the model? a.x1*x2 b.x1, x1*x2 c.x1, x2, x1*x2 d.Cannot conclude based on the provided information. 23

Multiple Choice Poll – Correct Answer The interaction term x1*x2 has a p-value of The p-value for x1 is 0.25 and the p-value for x2 is With a predetermined alpha of 0.05, what parameters should be included in the model? a.x1*x2 b.x1, x1*x2 c.x1, x2, x1*x2 d.Cannot conclude based on the provided information. 24

25

26 Chapter 5: Multiple Regression 5.1 Fitting a Multiple Regression Model 5.2 Fitting a Multiple Regression Model with Interactions 5.3 Generating and Comparing Candidate Models

27 Objectives Identify candidate models. Compute various statistics to evaluate candidate models. 27

28 Model Selection Eliminating one variable at a time manually for a small number of predictor variables is a reasonable approach numerous predictor variables can take a lot of time. 28

29 Generating Candidate Models with Stepwise Regression 29 Forward Selection Backward Selection Mixed Selection

30 Model Comparison Statistics JMP software provides several metrics to compare competing regression models including the following: Root Mean Square Error (RMSE)  smaller is better Adjusted R 2  bigger is better Mallows’ C p  look for models with C p  p, where p equals the number of parameters in the model, including the intercept Akaike’s Information Criterion, corrected (AIC c )  smaller is better Schwartz’s Bayesian Information Criterion (BIC)  smaller is better 30

31 This demonstration illustrates the concepts discussed previously. Generating and Comparing Candidate Models

32 Model Comparison Statistics Summary STATISTIC BACKWARD 5-PREDICTOR MODEL FORWARD 6-PREDICTOR MODEL RMSE Adjusted R AIC c BIC

33

34 This exercise reinforces the concepts discussed previously. Exercise

Quiz In the stepwise regression shown, why are some variables included when their p-value is greater than 0.05? 35

Quiz – Correct Answer In the stepwise regression shown, why are some variables included when their p-value is greater than 0.05? This model selection is based on Minimum BIC. The model with the lowest BIC value includes Age and MaxPulse. 36