Business Statistics - QBM117 Statistical inference for regression.

Slides:



Advertisements
Similar presentations
Assumptions underlying regression analysis
Advertisements

Simple Linear Regression Analysis
11-1 Empirical Models Many problems in engineering and science involve exploring the relationships between two or more variables. Regression analysis.
Forecasting Using the Simple Linear Regression Model and Correlation
Inference for Regression
6-1 Introduction To Empirical Models 6-1 Introduction To Empirical Models.
Regression Analysis Simple Regression. y = mx + b y = a + bx.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc Chapter 17 Simple Linear Regression and Correlation.
LINEAR REGRESSION: Evaluating Regression Models Overview Assumptions for Linear Regression Evaluating a Regression Model.
Chapter 10 Simple Regression.
Statistics for Managers Using Microsoft Excel, 5e © 2008 Prentice-Hall, Inc.Chap 13-1 Statistics for Managers Using Microsoft® Excel 5th Edition Chapter.
Pengujian Parameter Koefisien Korelasi Pertemuan 04 Matakuliah: I0174 – Analisis Regresi Tahun: Ganjil 2007/2008.
REGRESSION MODEL ASSUMPTIONS. The Regression Model We have hypothesized that: y =  0 +  1 x +  | | + | | So far we focused on the regression part –
Chapter Topics Types of Regression Models
Lecture 20 Simple linear regression (18.6, 18.9)
Regression Diagnostics - I
1 Simple Linear Regression and Correlation Chapter 17.
Simple Linear Regression Analysis
Business Statistics - QBM117 Interval estimation for the slope and y-intercept Hypothesis tests for regression.
Introduction to Probability and Statistics Linear Regression and Correlation.
Regression Diagnostics Checking Assumptions and Data.
Chapter 11: Inference for Distributions
Korelasi dalam Regresi Linear Sederhana Pertemuan 03 Matakuliah: I0174 – Analisis Regresi Tahun: Ganjil 2007/2008.
© 2000 Prentice-Hall, Inc. Chap Forecasting Using the Simple Linear Regression Model and Correlation.
Pertemua 19 Regresi Linier
1 Simple Linear Regression Chapter Introduction In Chapters 17 to 19 we examine the relationship between interval variables via a mathematical.
Correlation and Regression Analysis
Chapter 7 Forecasting with Simple Regression
Introduction to Regression Analysis, Chapter 13,
Copyright ©2006 Brooks/Cole, a division of Thomson Learning, Inc. More About Regression Chapter 14.
Simple Linear Regression Analysis
1 Simple Linear Regression 1. review of least squares procedure 2. inference for least squares lines.
Correlation & Regression
Introduction to Linear Regression and Correlation Analysis
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 12-1 Chapter 12 Simple Linear Regression Statistics for Managers Using.
Chapter 11 Simple Regression
STA291 Statistical Methods Lecture 27. Inference for Regression.
Linear Regression Inference
1 Least squares procedure Inference for least squares lines Simple Linear Regression.
Inferences for Regression
OPIM 303-Lecture #8 Jose M. Cruz Assistant Professor.
© 2003 Prentice-Hall, Inc.Chap 13-1 Basic Business Statistics (9 th Edition) Chapter 13 Simple Linear Regression.
Applied Quantitative Analysis and Practices LECTURE#23 By Dr. Osman Sadiq Paracha.
Introduction to Probability and Statistics Thirteenth Edition Chapter 12 Linear Regression and Correlation.
© Copyright McGraw-Hill Correlation and Regression CHAPTER 10.
REGRESSION DIAGNOSTICS Fall 2013 Dec 12/13. WHY REGRESSION DIAGNOSTICS? The validity of a regression model is based on a set of assumptions. Violation.
Lecture 10: Correlation and Regression Model.
Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin Simple Linear Regression Analysis Chapter 13.
McGraw-Hill/IrwinCopyright © 2009 by The McGraw-Hill Companies, Inc. All Rights Reserved. Simple Linear Regression Analysis Chapter 13.
Linear Correlation (12.5) In the regression analysis that we have considered so far, we assume that x is a controlled independent variable and Y is an.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc Chapter 17 Simple Linear Regression and Correlation.
Lecturer: Ing. Martina Hanová, PhD.. Regression analysis Regression analysis is a tool for analyzing relationships between financial variables:  Identify.
BUSINESS MATHEMATICS & STATISTICS. Module 6 Correlation ( Lecture 28-29) Line Fitting ( Lectures 30-31) Time Series and Exponential Smoothing ( Lectures.
Simple Linear Regression and Correlation (Continue..,) Reference: Chapter 17 of Statistics for Management and Economics, 7 th Edition, Gerald Keller. 1.
1 Simple Linear Regression Chapter Introduction In Chapters 17 to 19 we examine the relationship between interval variables via a mathematical.
Warm-Up The least squares slope b1 is an estimate of the true slope of the line that relates global average temperature to CO2. Since b1 = is very.
Inference for Least Squares Lines
Linear Regression.
Statistics for Managers using Microsoft Excel 3rd Edition
Keller: Stats for Mgmt & Econ, 7th Ed
Chapter 12: Regression Diagnostics
BA 275 Quantitative Business Methods
Chapter 4, Regression Diagnostics Detection of Model Violation
CHAPTER 12 More About Regression
Regression Assumptions
Chapter 13 Additional Topics in Regression Analysis
Inferences for Regression
Regression and Correlation of Data
Regression Assumptions
Presentation transcript:

Business Statistics - QBM117 Statistical inference for regression

Objectives w To define the linear model which defines the population of interest. w To explain the required conditions of the error variable. w Regression diagnostics

w we have learnt how to estimate the strength of the relationship between the variables using the correlation ceoefficient; w we have learnt how to estimate the relationship between the variables using the least squares regression line, and w we have learnt to estimate the accuracy of the line for prediction, using the standard error of estimate and the coefficient of determination. In the previous two lectures, we have concentrated on summarising sample bivariate data: We now need to perform statistical inference about the population, from which these samples have been taken, in order to better understand the larger population.

The linear model What is the appropriate population for a simple linear regression problem? Where y = the observed value in the population = the straight line population relationship = the error variable Therefore the least squares regression line estimates the population relationship described by the linear model and, The linear model is the basic assumption required for statistical inference in regression and correlation.

Required conditions of the error variable Similarly, the statistical tests we perform in hypothesis testing will only be valid, is these conditions are satisfied. So what are these conditions? will only provide good estimates for if certain assumptions about the error variable are valid.

w The probability distribution of  is normal. w The mean of the distribution is zero ie E(  ) = 0 w The variance of ,  2  is constant, no matter what the value of x. w The errors associated with any two y values are independent. As a result, the value of the error variable at one point does not affect the value of the error variable at another point. Required conditions of the error variable

Requirements 1, 2, and 3 can be interpreted in another way: For each value of x, y is a normally distributed random variable whose mean is And whose standard deviation is Since the mean depends on x, the expected value is often expressed as The standard deviation however is not influenced by x, because it is constant for all values of x.

X Y E[Y]=  0 +  1 X Asumptions of the Simple Linear Regression Model Identical normal distributions of errors, all centered on the regression line.

w Most departures from the required conditions can be diagnosed by examining the residuals. w Excel allows us to calculate these residuals and apply various graphical techniques to them. w Analysis of the residuals allow us to determine whether the variance of the error variable is constant and whether the errors are independent. w Excel can also generate standardised residuals. The residuals are standardised in the usual way, by subtracting the mean (0 in this case) and dividing by the standard deviation (or its estimate in this case, s  ) Regression diagnostics

Non-normality We can check for normality by drawing a histogram of the residuals to see if it appears that the error variable is normally distributed. Since the tests in regression analysis are robust, as long as the histogram at least resembles an approximate bell shape or is not extremely non-normal, it is safe to assume that the normality requirement has been met.

Expectation of zero The use of the method of least squares to find the line of best fit ensures that this will always be the case. We can however observe from the histogram of the residuals, that the residuals are approximately symmetric about a value which is close to zero.

Heteroscedasticity The variance of the error variable, constant. When this requirement is violated, the condition is called heteroscedasticity. is required to be Homoscedasticity refers to the condition when the requirement is satisfied. One method of diagnosing heteroscedasticity is to plot the residuals against the x values or the predicted values of y and look for any change in the spread of the variation of the residuals.

Residual Analysis and Checking for Model Inadequacies

Non-independence of the error term w This requirement states that the values of the error variable must be independent. w If the data are time series data, the errors are often correlated w Error terms which are correlated over time are said to be autocorrelated or serially correlated. w We can often detect autocorrelation if we plot the residuals against the time period. w If a pattern emerges, it is likely that the independence requirement is violated.

Reading for next lecture Read Chapter 18 Sections 18.5 and 18.7 (Chapter 11 Sections 11.5 and 11.7 abridged)