Statistics 350 Lecture 10. Today Last Day: Start Chapter 3 Today: Section 3.8 Homework #3: Chapter 2 Problems (page 89-99): 13, 16,55, 56 Due: February.

Slides:



Advertisements
Similar presentations
Assumptions underlying regression analysis
Advertisements

Regression Analysis Simple Regression. y = mx + b y = a + bx.
Class 16: Thursday, Nov. 4 Note: I will you some info on the final project this weekend and will discuss in class on Tuesday.
Stat 112: Lecture 15 Notes Finish Chapter 6: –Review on Checking Assumptions (Section ) –Outliers and Influential Points (Section 6.7) Homework.
BA 555 Practical Business Analysis
Lecture 25 Multiple Regression Diagnostics (Sections )
Class 5: Thurs., Sep. 23 Example of using regression to make predictions and understand the likely errors in the predictions: salaries of teachers and.
Lecture 19: Tues., Nov. 11th R-squared (8.6.1) Review
Class 6: Tuesday, Sep. 28 Section 2.4. Checking the assumptions of the simple linear regression model: –Residual plots –Normal quantile plots Outliers.
Statistics 350 Lecture 11. Today Last Day: Start Chapter 3 Today: Section 3.8 Mid-Term Friday…..Sections ; ; (READ)
Lecture 24 Multiple Regression (Sections )
REGRESSION MODEL ASSUMPTIONS. The Regression Model We have hypothesized that: y =  0 +  1 x +  | | + | | So far we focused on the regression part –
Lecture 20 Simple linear regression (18.6, 18.9)
Regression Diagnostics - I
Stat Today: Multiple comparisons, diagnostic checking, an example After these notes, we will have looked at (skip figures 1.2 and 1.3, last.
Stat 112: Lecture 13 Notes Finish Chapter 5: –Review Predictions in Log-Log Transformation. –Polynomials and Transformations in Multiple Regression Start.
1 4. Multiple Regression I ECON 251 Research Methods.
Regression Diagnostics Checking Assumptions and Data.
Lecture 19 Transformations, Predictions after Transformations Other diagnostic tools: Residual plot for nonconstant variance, histogram to check normality.
Statistics 350 Lecture 8. Today Last Day: Finish last day Today: Old Faithful, Start Chapter 3.
Stat 112 Notes 11 Today: –Fitting Curvilinear Relationships (Chapter 5) Homework 3 due Friday. I will Homework 4 tonight, but it will not be due.
Statistics 350 Lecture 17. Today Last Day: Introduction to Multiple Linear Regression Model Today: More Chapter 6.
Class 11: Thurs., Oct. 14 Finish transformations Example Regression Analysis Next Tuesday: Review for Midterm (I will take questions and go over practice.
Stat 112: Lecture 16 Notes Finish Chapter 6: –Influential Points for Multiple Regression (Section 6.7) –Assessing the Independence Assumptions and Remedies.
Business Statistics - QBM117 Statistical inference for regression.
Transforming the data Modified from: Gotelli and Allison Chapter 8; Sokal and Rohlf 2000 Chapter 13.
Correlation & Regression
Regression and Correlation Methods Judy Zhong Ph.D.
1 Least squares procedure Inference for least squares lines Simple Linear Regression.
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Chapter 3: Diagnostics and Remedial Measures
Economics 173 Business Statistics Lecture 20 Fall, 2001© Professor J. Petry
Chapter 14 Inference for Regression © 2011 Pearson Education, Inc. 1 Business Statistics: A First Course.
Regression Analysis Week 8 DIAGNOSTIC AND REMEDIAL MEASURES Residuals The main purpose examining residuals Diagnostic for Residuals Test involving residuals.
Stat 112 Notes 16 Today: –Outliers and influential points in multiple regression (Chapter 6.7)
Maths Study Centre CB Open 11am – 5pm Semester Weekdays
© Buddy Freeman, Independence of error assumption. In many business applications using regression, the independent variable is TIME. When the data.
1 Regression Analysis The contents in this chapter are from Chapters of the textbook. The cntry15.sav data will be used. The data collected 15 countries’
Model Selection and Validation. Model-Building Process 1. Data collection and preparation 2. Reduction of explanatory or predictor variables (for exploratory.
REGRESSION DIAGNOSTICS Fall 2013 Dec 12/13. WHY REGRESSION DIAGNOSTICS? The validity of a regression model is based on a set of assumptions. Violation.
Stat 112 Notes 10 Today: –Fitting Curvilinear Relationships (Chapter 5) Homework 3 due Thursday.
Chapter 12: Correlation and Linear Regression 1.
Stat 112 Notes 5 Today: –Chapter 3.7 (Cautions in interpreting regression results) –Normal Quantile Plots –Chapter 3.6 (Fitting a linear time trend to.
KNN Ch. 3 Diagnostics and Remedial Measures Applied Regression Analysis BUSI 6220.
8-1 MGMG 522 : Session #8 Heteroskedasticity (Ch. 10)
Stat 112 Notes 14 Assessing the assumptions of the multiple regression model and remedies when assumptions are not met (Chapter 6).
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc Chapter 17 Simple Linear Regression and Correlation.
Maths Study Centre CB Open 11am – 5pm Semester Weekdays
732G21/732G28/732A35 Lecture 3. Properties of the model errors ε 4. ε are assumed to be normally distributed
Stat 112 Notes 11 Today: –Transformations for fitting Curvilinear Relationships (Chapter 5)
Chapter 12: Correlation and Linear Regression 1.
Simple Linear Regression and Correlation (Continue..,) Reference: Chapter 17 of Statistics for Management and Economics, 7 th Edition, Gerald Keller. 1.
Statistics 350 Lecture 2. Today Last Day: Section Today: Section 1.6 Homework #1: Chapter 1 Problems (page 33-38): 2, 5, 6, 7, 22, 26, 33, 34,
Quantitative Methods Residual Analysis Multiple Linear Regression C.W. Jackson/B. K. Gordor.
Chapter 13 Lesson 13.2a Simple Linear Regression and Correlation: Inferential Methods 13.2: Inferences About the Slope of the Population Regression Line.
Chapter 12: Correlation and Linear Regression 1.
Lecture Slides Elementary Statistics Twelfth Edition
Inference for Least Squares Lines
Statistical Data Analysis - Lecture /04/03
Statistics 350 Lecture 4.
Chapter 12: Regression Diagnostics
Regression Models - Introduction
Undergraduated Econometrics
Regression is the Most Used and Most Abused Technique in Statistics
Simple Linear Regression
Regression Assumptions
Chapter 13 Additional Topics in Regression Analysis
Problems of Tutorial 9 (Problem 4.12, Page 120) Download the “Data for Exercise ” from the class website. The data consist of 1 response variable.
Regression Assumptions
Regression Models - Introduction
Presentation transcript:

Statistics 350 Lecture 10

Today Last Day: Start Chapter 3 Today: Section 3.8 Homework #3: Chapter 2 Problems (page 89-99): 13, 16,55, 56 Due: February 7 Read Sections Mid-Term next Friday…..Sections ; ; (READ)

Overview of Remedial Measures for Model Violations Suppose you do a scatter plot of Y vs. X, and decide to attempt to regress Y on X Next, you test the simple linear regression model assumption using the plots discussed last day If you decide that model (2.1) is not appropriate, then there are three options: 1 2 3

Overview of Remedial Measures for Model Violations If there is a problem with non-linearity of the regression function: If there is a problem with non-constant error variance:

Overview of Remedial Measures for Model Violations If there is a problem with lack of independence among errors: If there is a problem with non-normality of error terms:

Overview of Remedial Measures for Model Violations If there are omitted explanatory variables: If there are outliers: What to do with outliers once you find them is the tricky part. Outliers are the most interesting observations in your data, and every effort should be made to determine why they occurred. This isn't always possible. General recommendations:

Transformations Sometimes simple transformations of X and/or Y may make the simple linear regression model appropriate for the transformed data Especially when:

Transformations If the problem is non-linearity of the regression function, a transformation of X often helps This is particularly true when the distribution of the error terms is close to normal and the variance appears to be approximately constant

Transformations Note:

Transformations Transforming X will not help address non-normality of the errors More helpful to attempt to transform Y Let Y`=h(Y) for some function h( ), and perform a simple linear regression using the Y`…must still do usual model validation for the new fitted model

Transformations Transformation of Y affects the shape of the regression function, the variance of the errors and the distribution of the error terms Is a good idea when all these violation appear On the other hand, when only one of these violations is evident, transforming Y can cause problems with the other two For example, if the straight line seems to fit well, but the variances of residuals are changing, the transformation of Y will create curvature in the regression function, causing a bad fit.

Transformations Suppose true linear response is on the log scale: This implies that: In these situation, variance tends to increase with the mean because of the

Transformations Nothing stops you from transforming both sides Do this when:

Transformations Common transformations: