Simple Linear Regression Chapter 11 Simple Linear Regression
Learning Objectives 1. Describe the Linear Regression Model 2. State the Regression Modeling Steps Explain Ordinary Least Squares Understand and check model assumptions 4. Compute Regression Coefficients 5. Predict Response Variable 6. Interpret Computer Output As a result of this class, you will be able to...
Models 3
Models 1. Representation of Some Phenomenon 2. Mathematical Model Is a Mathematical Expression of Some Phenomenon 3. Often Describe Relationships between Variables 4. Types Deterministic Models Probabilistic Models .
Deterministic Models 1. Hypothesize Exact Relationships 2. Suitable When Prediction Error is Negligible 3. Example: Force Is Exactly Mass Times Acceleration F = m·a © 1984-1994 T/Maker Co.
Probabilistic Models 1. Hypothesize 2 Components Deterministic Random Error 2. Example: Sales Volume Is 10 Times Advertising Spending + Random Error Y = 10X + Random Error May Be Due to Factors Other Than Advertising
Types of Probabilistic Models 7
Regression Models 13
Types of Probabilistic Models 7
Regression Models 1. Answer ‘What Is the Relationship Between the Variables?’ 2. Equation Used 1 Numerical Dependent (Response) Variable What Is to Be Predicted 1 or More Numerical or Categorical Independent (Explanatory) Variables 3. Used Mainly for Prediction & Estimation
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Model Specification 13
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Specifying the Model 1. Define Variables 2. Hypothesize Nature of Relationship Expected Effects (i.e., Coefficients’ Signs) Functional Form (Linear or Non-Linear) Interactions
Model Specification Is Based on Theory 1. Theory of Field (e.g., Sociology) 2. Mathematical Theory 3. Previous Research 4. ‘Common Sense’
Thinking Challenge: Which Is More Logical? With positive linear relationship, sales increases infinitely. Discuss concept of ‘relevant range’. 17
Types of Regression Models This teleology is based on the number of explanatory variables & nature of relationship between X & Y. 18
Types of Regression Models This teleology is based on the number of explanatory variables & nature of relationship between X & Y. 19
Types of Regression Models 1 Explanatory Variable Models This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple 20
Types of Regression Models 1 Explanatory 2+ Explanatory Variable Models Variables This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple Multiple 21
Types of Regression Models 1 Explanatory 2+ Explanatory Variable Models Variables This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple Multiple Linear 22
Types of Regression Models 1 Explanatory 2+ Explanatory Variable Models Variables This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple Multiple Non- Linear Linear 23
Types of Regression Models 1 Explanatory 2+ Explanatory Variable Models Variables This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple Multiple Non- Linear Linear Linear 24
Types of Regression Models 1 Explanatory 2+ Explanatory Variable Models Variables This teleology is based on the number of explanatory variables & nature of relationship between X & Y. Simple Multiple Non- Non- Linear Linear Linear Linear 24
Linear Regression Model 26
Types of Regression Models This teleology is based on the number of explanatory variables & nature of relationship between X & Y. 27
Linear Equations High School Teacher © 1984-1994 T/Maker Co. 28
Linear Regression Model 1. Relationship Between Variables Is a Linear Function Population Y-Intercept Population Slope Random Error Y X i 1 i i Dependent (Response) Variable (e.g., income) Independent (Explanatory) Variable (e.g., education)
Population & Sample Regression Models 30
Population & Sample Regression Models $ $ $ $ $ 31
Population & Sample Regression Models Unknown Relationship $ $ $ $ $ 32
Population & Sample Regression Models Random Sample Unknown Relationship $ $ $ $ $ $ $ 33
Population & Sample Regression Models Random Sample Unknown Relationship $ $ $ $ $ $ $ 34
Population Linear Regression Model Observedvalue i = Random error Observed value 35
Sample Linear Regression Model i = Random error ^ Unsampled observation Observed value 36
Estimating Parameters: Least Squares Method 40
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Scattergram 1. Plot of All (Xi, Yi) Pairs 2. Suggests How Well Model Will Fit Y 60 40 20 X 20 40 60
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 42
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 43
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 44
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 45
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 46
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 47
Thinking Challenge How would you draw a line through the points? How do you determine which line ‘fits best’? 48
Least Squares 1. ‘Best Fit’ Means Difference Between Actual Y Values & Predicted Y Values Are a Minimum But Positive Differences Off-Set Negative 49
Least Squares 1. ‘Best Fit’ Means Difference Between Actual Y Values & Predicted Y Values Are a Minimum But Positive Differences Off-Set Negative 50
Least Squares 1. ‘Best Fit’ Means Difference Between Actual Y Values & Predicted Y Values Are a Minimum But Positive Differences Off-Set Negative 2. LS Minimizes the Sum of the Squared Differences (SSE) 51
Least Squares Graphically 52
Coefficient Equations Prediction Equation Sample Slope Sample Y-intercept 53
Computation Table 54
Interpretation of Coefficients
Interpretation of Coefficients ^ 1. Slope (1) Estimated Y Changes by 1 for Each 1 Unit Increase in X If 1 = 2, then Sales (Y) Is Expected to Increase by 2 for Each 1 Unit Increase in Advertising (X) ^ ^
Interpretation of Coefficients ^ 1. Slope (1) Estimated Y Changes by 1 for Each 1 Unit Increase in X If 1 = 2, then Sales (Y) Is Expected to Increase by 2 for Each 1 Unit Increase in Advertising (X) 2. Y-Intercept (0) Average Value of Y When X = 0 If 0 = 4, then Average Sales (Y) Is Expected to Be 4 When Advertising (X) Is 0 ^ ^ ^ ^
Parameter Estimation Example You’re a marketing analyst for Hasbro Toys. You gather the following data: Ad $ Sales (Units) 1 1 2 1 3 2 4 2 5 4 What is the relationship between sales & advertising?
Scattergram Sales vs. Advertising 57
Guess The Parameters!
Scattergram Sales vs. Advertising 57
Parameter Estimation Solution Table 58
Parameter Estimation Solution 59
Coefficient Interpretation Solution
Coefficient Interpretation Solution ^ 1. Slope (1) Sales Volume (Y) Is Expected to Increase by .7 Units for Each $1 Increase in Advertising (X)
Coefficient Interpretation Solution ^ 1. Slope (1) Sales Volume (Y) Is Expected to Increase by .7 Units for Each $1 Increase in Advertising (X) 2. Y-Intercept (0) Average Value of Sales Volume (Y) Is -.10 Units When Advertising (X) Is 0 Difficult to Explain to Marketing Manager Expect Some Sales Without Advertising ^
Parameter Estimation Computer Output Parameter Estimates Parameter Standard T for H0: Variable DF Estimate Error Param=0 Prob>|T| INTERCEP 1 -0.1000 0.6350 -0.157 0.8849 ADVERT 1 0.7000 0.1914 3.656 0.0354 ^ k ^ ^ 0 1
Derivation of Parameter Equations Goal: Minimize squared error
Derivation of Parameter Equations
Parameter Estimation Thinking Challenge You’re an economist for the county cooperative. You gather the following data: Fertilizer (lb.) Yield (lb.) 4 3.0 6 5.5 10 6.5 12 9.0 What is the relationship between fertilizer & crop yield? © 1984-1994 T/Maker Co. 62
Scattergram Crop Yield vs. Fertilizer* Yield (lb.) Fertilizer (lb.) 65
Parameter Estimation Solution Table* 66
Parameter Estimation Solution* 67
Coefficient Interpretation Solution*
Coefficient Interpretation Solution* ^ 1. Slope (1) Crop Yield (Y) Is Expected to Increase by .65 lb. for Each 1 lb. Increase in Fertilizer (X)
Coefficient Interpretation Solution* ^ 1. Slope (1) Crop Yield (Y) Is Expected to Increase by .65 lb. for Each 1 lb. Increase in Fertilizer (X) 2. Y-Intercept (0) Average Crop Yield (Y) Is Expected to Be 0.8 lb. When No Fertilizer (X) Is Used ^
Probability Distribution of Random Error 69
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Linear Regression Assumptions 1. Mean of Probability Distribution of Error Is 0 Probability Distribution of Error Has Constant Variance Exercise: Constant across what? 3. Probability Distribution of Error is Normal 4. Errors Are Independent
Error Probability Distribution ^ 91
Random Error Variation
Random Error Variation 1. Variation of Actual Y from Predicted Y
Random Error Variation 1. Variation of Actual Y from Predicted Y 2. Measured by Standard Error of Regression Model Sample Standard Deviation of , s ^
Random Error Variation 1. Variation of Actual Y from Predicted Y 2. Measured by Standard Error of Regression Model Sample Standard Deviation of , s 3. Affects Several Factors Parameter Significance Prediction Accuracy ^
Testing for Significance Evaluating the Model Testing for Significance 99
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Test of Slope Coefficient 1. Shows If There Is a Linear Relationship Between X & Y 2. Involves Population Slope 1 3. Hypotheses H0: 1 = 0 (No Linear Relationship) Ha: 1 0 (Linear Relationship) 4. Theoretical Basis Is Sampling Distribution of Slope
Sampling Distribution of Sample Slopes 102
Sampling Distribution of Sample Slopes 103
Sampling Distribution of Sample Slopes All Possible Sample Slopes Sample 1: 2.5 Sample 2: 1.6 Sample 3: 1.8 Sample 4: 2.1 : : Very large number of sample slopes 104
Sampling Distribution of Sample Slopes All Possible Sample Slopes Sample 1: 2.5 Sample 2: 1.6 Sample 3: 1.8 Sample 4: 2.1 : : Very large number of sample slopes Sampling Distribution S ^ 1 ^ 1 105
Slope Coefficient Test Statistic 106
Test of Slope Coefficient Example You’re a marketing analyst for Hasbro Toys. You find b0 = -.1, b1 = .7 & s = .60553. Ad $ Sales (Units) 1 1 2 1 3 2 4 2 5 4 Is the relationship significant at the .05 level?
Solution Table 108
Test of Slope Parameter Solution H0: 1 = 0 Ha: 1 0 .05 df 5 - 2 = 3 Critical Value(s): Test Statistic: Decision: Conclusion: Reject at = .05 There is evidence of a relationship 109
Test Statistic Solution
Test of Slope Parameter Computer Output Parameter Estimates Parameter Standard T for H0: Variable DF Estimate Error Param=0 Prob>|T| INTERCEP 1 -0.1000 0.6350 -0.157 0.8849 ADVERT 1 0.7000 0.1914 3.656 0.0354 ‘Standard Error’ is the estimated standard deviation of the sampling distribution, sbP. ^ ^ S ^ t = k / S k ^ k k P-Value
Measures of Variation in Regression 1. Total Sum of Squares (SSyy) Measures Variation of Observed Yi Around the MeanY 2. Explained Variation (SSR) Variation Due to Relationship Between X & Y 3. Unexplained Variation (SSE) Variation Due to Other Factors
Variation Measures Yi Unexplained sum of squares (Yi -Yi)2 ^ Total sum of squares (Yi -Y)2 Explained sum of squares (Yi -Y)2 ^ 78
Coefficient of Determination 1. Proportion of Variation ‘Explained’ by Relationship Between X & Y 0 r2 1 79
Coefficient of Determination Examples 80
Coefficient of Determination Example You’re a marketing analyst for Hasbro Toys. You find 0 = -0.1 & 1 = 0.7. Ad $ Sales (Units) 1 1 2 1 3 2 4 2 5 4 Interpret a coefficient of determination of 0.8167. ^ ^ 83
r 2 Computer Output Root MSE 0.60553 R-square 0.8167 Dep Mean 2.00000 Adj R-sq 0.7556 C.V. 30.27650 r2 r2 adjusted for number of explanatory variables & sample size S
Using the Model for Prediction & Estimation 112
Regression Modeling Steps 1. Hypothesize Deterministic Component 2. Estimate Unknown Model Parameters 3. Specify Probability Distribution of Random Error Term Estimate Standard Deviation of Error 4. Evaluate Model 5. Use Model for Prediction & Estimation
Prediction With Regression Models 1. Types of Predictions Point Estimates Interval Estimates 2. What Is Predicted Population Mean Response E(Y) for Given X Point on Population Regression Line Individual Response (Yi) for Given X
What Is Predicted 115
Confidence Interval Estimate of Mean Y
Factors Affecting Interval Width 1. Level of Confidence (1 - ) Width Increases as Confidence Increases 2. Data Dispersion (s) Width Increases as Variation Increases 3. Sample Size Width Decreases as Sample Size Increases 4. Distance of Xp from MeanX Width Increases as Distance Increases
Why Distance from Mean? X Greater dispersion than X1 The closer to the mean, the less variability. This is due to the variability in estimated slope parameters. X 118
Confidence Interval Estimate Example You’re a marketing analyst for Hasbro Toys. You find b0 = -.1, b1 = .7 & s = .60553. Ad $ Sales (Units) 1 1 2 1 3 2 4 2 5 4 Estimate the mean sales when advertising is $4 at the .05 level.
Solution Table 120
Confidence Interval Estimate Solution X to be predicted 121
Prediction Interval of Individual Response Note the 1 under the radical in the standard error formula. The effect of the extra Syx is to increase the width of the interval. This will be seen in the interval bands. Note! 122
Why the Extra ‘S’? The error in predicting some future value of Y is the sum of 2 errors: 1. the error of estimating the mean Y, E(Y|X) 2. the random error that is a component of the value of Y to be predicted. Even if we knew the population regression line exactly, we would still make error. 123
Interval Estimate Computer Output Dep Var Pred Std Err Low95% Upp95% Low95% Upp95% Obs SALES Value Predict Mean Mean Predict Predict 1 1.000 0.600 0.469 -0.892 2.092 -1.837 3.037 2 1.000 1.300 0.332 0.244 2.355 -0.897 3.497 3 2.000 2.000 0.271 1.138 2.861 -0.111 4.111 4 2.000 2.700 0.332 1.644 3.755 0.502 4.897 5 4.000 3.400 0.469 1.907 4.892 0.962 5.837 Predicted Y when X = 4 Confidence Interval Prediction Interval SY ^
Hyperbolic Interval Bands Note: 1. As we move farther from the mean, the bands get wider. 2. The prediction interval bands are wider. Why? (extra Syx) 124
Correlation Models 129
Types of Probabilistic Models 130
Correlation Models 1. Answer ‘How Strong Is the Linear Relationship Between 2 Variables?’ 2. Coefficient of Correlation Used Population Correlation Coefficient Denoted (Rho) Values Range from -1 to +1 Measures Degree of Association 3. Used Mainly for Understanding
Sample Coefficient of Correlation 1. Pearson Product Moment Coefficient of Correlation, r: 132
Coefficient of Correlation Values -1.0 -.5 +.5 +1.0 134
Coefficient of Correlation Values No Correlation -1.0 -.5 +.5 +1.0 135
Coefficient of Correlation Values No Correlation -1.0 -.5 +.5 +1.0 Increasing degree of negative correlation 136
Coefficient of Correlation Values Perfect Negative Correlation No Correlation -1.0 -.5 +.5 +1.0 137
Coefficient of Correlation Values Perfect Negative Correlation No Correlation -1.0 -.5 +.5 +1.0 Increasing degree of positive correlation 138
Coefficient of Correlation Values Perfect Negative Correlation Perfect Positive Correlation No Correlation -1.0 -.5 +.5 +1.0 139
Coefficient of Correlation Examples 141
Test of Coefficient of Correlation 1. Shows If There Is a Linear Relationship Between 2 Numerical Variables 2. Same Conclusion as Testing Population Slope 1 3. Hypotheses H0: = 0 (No Correlation) Ha: 0 (Correlation)
Conclusion 1. Described the Linear Regression Model 2. Stated the Regression Modeling Steps 3. Explained Ordinary Least Squares 4. Computed Regression Coefficients 5. Predicted Response Variable 6. Interpreted Computer Output
Any blank slides that follow are blank intentionally. End of Chapter Any blank slides that follow are blank intentionally.