Lecture Business statistics in practice (7/e): Chapter 14 - Bowerman, O'Connell, Murphree

Chia sẻ: Fff Fff | Ngày: | Loại File: PPT | Số trang:14

Thêm vào BST

Báo xấu

52
lượt xem 1
download

Download Vui lòng tải xuống để xem tài liệu đầy đủ

Chapter 14 - Simple linear regression analysis. After mastering the material in this chapter, you will be able to: Explain the simple linear regression model, find the least squares point estimates of the slope and y-intercept, describe the assumptions behind simple linear regression and calculate the standard error,...

Chủ đề:

Bình luận(0) Đăng nhập để gửi bình luận!

Lưu

Nội dung Text: Lecture Business statistics in practice (7/e): Chapter 14 - Bowerman, O'Connell, Murphree

Chapter 14 Simple Linear Regression Analysis McGrawHill/Irwin Copyright © 2014 by The McGrawHill Companies, Inc. All rights reserved.
Simple Linear Regression Analysis 14.1 The Simple Linear Regression Model and the Least Square Point Estimates 14.2 Model Assumptions and the Standard Error 14.3 Testing the Significance of Slope and y Intercept 14.4 Confidence and Prediction Intervals 14.5 Simple Coefficients of Determination and Correlation 142
Simple Linear Regression Analysis Continued 14.6 Testing the Significance of the Population Correlation Coefficient 14.7 An F Test for the Model 14.8 The QHIC Case 14.9 Residual Analysis 14.10 Some Shortcut Formulas (Optional) 143
LO14-1: Explain the simple linear regression 14.1 The Simple Linear Regression Model model. and the Least Squares Point Estimates  The dependent (or response) variable is the variable we wish to understand or predict  The independent (or predictor) variable is the variable we will use to understand or predict the dependent variable  Regression analysis is a statistical technique that uses observed data to relate the dependent variable to one or more independent variables  The objective is to build a regression model that can describe, predict and control the dependent variable based on the independent variable 144
LO14-1 Form of The Simple Linear Regression Model y = β0 + β1x + ε  = β0 + β1x + ε is the mean value of the y dependent variable y when the value of the independent variable is x β0 is the yintercept; the mean of y when x is 0 β1 is the slope; the change in the mean of y per unit change in x ε is an error term that describes the effect on y of all factors other than x 145
LO14-1 Regression Terms β0 and β1 are called regression parameters β0 is the yintercept and β1 is the slope We do not know the true values of these parameters So, we must use sample data to estimate them b0 is the estimate of β0 and b1 is the estimate of β1 146
LO14-2: Find the least squares point estimates of the slope and y- The Least Squares Point Estimates intercept. Estimation/prediction equation ŷ = b0 + b1x Least squares point estimate of the slope β1 SS xy b1 SS xx xi yi SS xy ( xi x ) ( yi y) xi yi n 2 2 xi SS xx ( xi x) xi2 n yi xi b0 y b1 x y x n n Least squares point estimate of yintercept 0 147
LO14-3: Describe the assumptions behind simple linear regression and calculate the standard error. 14.2 Model Assumptions and the Standard Error 1. Mean of Zero At any given value of x, the population of potential error term values has a mean equal to zero 2. Constant Variance Assumption At any given value of x, the population of potential error term values has a variance that does not depend on the value of x 3. Normality Assumption At any given value of x, the population of potential error term values has a normal distribution 4. Independence Assumption Any one value of the error term ε is statistically independent of any other value of ε Figure 14.7 148
LO14-4: Test the significance of the slope and y-intercept. 14.3 Testing the Significance of the Slope and yIntercept A regression model is not likely to be useful unless there is a significant relationship between x and y To test significance, we use the null hypothesis: H0: β1 = 0 Versus the alternative hypothesis: Ha: β1 ≠ 0 149
LO14-5: Calculate and interpret a confidence interval for a mean value and a prediction interval for an individual 14.4 Confidence and Prediction value. Intervals  The point on the regression line corresponding to a particular value of x0 of the independent variable x is ŷ = b0 + b1x0  It is unlikely that this value will equal the mean value of y when x equals x0  Therefore, we need to place bounds on how far the predicted value might be from the actual value  We can do this by calculating a confidence interval mean for the value of y and a prediction interval for an individual value of y 1410
LO 6: Calculate and interpret the simple coefficients of determination and correlation. 14.5 Simple Coefficient of Determination and Correlation How useful is a particular regression model? One measure of usefulness is the simple coefficient of determination It is represented by the symbol r2 This section may be covered anytime after reading Section 14.1 1411
LO14-7: Test hypotheses about the population correlation coefficient. 14.6 Testing the Significance of the Population Correlation Coefficient The simple correlation coefficient (r) measures the linear relationship between the observed values of x and y from the sample The population correlation coefficient (ρ) measures the linear relationship between all possible combinations of observed values of x and y r is an estimate of ρ 1412
LO14-8: Test the significance of a simple linear regression model 14.7 An F Test for Model by using an F test. For simple regression, this is another way to test the null hypothesis H0: β1 = 0 This is the only test we will use for multiple regression The F test tests the significance of the overall regression relationship between x and y 1413
LO14-9: Use residual analysis to check the assumptions of simple 14.9 Residual Analysis linear regression. Checks of regression assumptions are performed by analyzing the regression residuals Residuals (e) are defined as the difference between the observed value of y and the predicted value of y, e = y ŷ ◦Note that e is the point estimate of ε If regression assumptions valid, the population of potential error terms will be normally distributed with mean zero and variance σ2 Different error terms will be statistically independent 1414