MULTIPLE REGRESSION
An illustrated tutorial and introduction to multiple linear regression analysis using SPSS, SAS, or Stata. Suitable for introductory graduate-level study.
The 2014 edition is a major update to the 2012 edition. Among the new features are these:
* Now includes worked examples for SPSS, SAS, and Stata.
* Was 180 pages with 70 illustrations, now 410 pages with over 300 illustrations.
* Thoroughly revised and updated throughout.
* Now covers quantile regression, needed for heterosccedastic models
* Now covers difference in differences regression.
* Now covers robust regression (not just regression w/ robust standard errors)
* Greatly expanded coverage of residual analysis.
* Greatly expanded coverage of model selection regression
* New section on plotting interactions through simple slope analysis
* Links to all datasets used in the text.
Partial table of contents:
Overview13
Data examples in this volume16
Key Terms and Concepts17
OLS estimation17
The regression equation18
Dependent variable20
Independent variables21
Dummy variables21
Interaction effects22
Interactions22
Centering23
Significance of interaction effects23
Interaction terms with categorical dummies24
Plotting interactions through simple slope analysis24
Separate regressions27
Predicted values28
SPSS28
SAS28
Stata29
Adjusted predicted values30
Residuals31
Centering31
OLS regression in SPSS32
Example32
SPSS input32
SPSS Output33
The regression coefficient, b33
Interpreting b for dummy variables34
Confidence limits on b35
Beta weights35
Zero-order, partial, and part correlations36
R2 and the “Model Summary” table39
The Anova table40
Tolerance and VIF collinearity statistics40
SPSS plots41
SPSS “Plots” dialog41
Plot of standardized residuals against standardized predicted values43
Histogram of standardized residuals44
Normal probability (P-P) plot45
OLS regression in SAS46
Example46
SAS input47
SAS output48
The regression coefficient, b48
Interpreting b for dummy variables49
Confidence limits on b49
Beta weights50
Zero order, partial, and part correlation52
R-Squared and the Anova table53
Tolerance and VIF collinearity statistics54
SAS Plots55
SAS plotting options55
Plot of residuals against predicted values57
Histogram and kernel density plot of standardized residuals58
Normal probability (P-P) plot59
Normal quantile-quantile (Q-Q) plot60
Other SAS plots61
OLS regression in Stata64
Example64
Stata input65
Stata output66
The regression coefficient, b66
Interpreting b coefficients67
Confidence limits on b68
Beta weights68
R-Squared and the Anova table68
Zero order, partial, and part correlation69
Tolerance and VIF collinearity statistics69
Other Stata postestimation output70
Stata Plots71
Stata plotting options71
Plot of standardized residuals against standardized predicted values71
Histogram of standardized residuals73
Normal probability (P-P) plot74
Margin plots75
Robust regression75
Overview75
When to use robust regression76
Robust regression in SPSS76
Overview76
SPSS input77
SPSS output77
Robust regression in SAS78
SAS input78
SAS output80
Robust regression in Stata81
Stata input81
Stata output81
Hierarchical multiple regression82
Overview82
Examples83
Difference in differences regression83
Overview83
The parallel trend assumption84
Example data85
Data setup86
The model86
Difference modeling in SPSS89
SPSS input89
Should the dependent variable be linear or logarithmic?90
SPSS output92
Difference modeling in SAS94
SAS input94
Should the dependent variable be linear or logarithmic?95
SAS output96
Difference modeling in Stata98
Stata input98
Should the dependent variable be linear or logarithmic?98
Stata output99
Panel data regression101
Overview101
Types of panel data regression1
An illustrated tutorial and introduction to multiple linear regression analysis using SPSS, SAS, or Stata. Suitable for introductory graduate-level study.
The 2014 edition is a major update to the 2012 edition. Among the new features are these:
* Now includes worked examples for SPSS, SAS, and Stata.
* Was 180 pages with 70 illustrations, now 410 pages with over 300 illustrations.
* Thoroughly revised and updated throughout.
* Now covers quantile regression, needed for heterosccedastic models
* Now covers difference in differences regression.
* Now covers robust regression (not just regression w/ robust standard errors)
* Greatly expanded coverage of residual analysis.
* Greatly expanded coverage of model selection regression
* New section on plotting interactions through simple slope analysis
* Links to all datasets used in the text.
Partial table of contents:
Overview13
Data examples in this volume16
Key Terms and Concepts17
OLS estimation17
The regression equation18
Dependent variable20
Independent variables21
Dummy variables21
Interaction effects22
Interactions22
Centering23
Significance of interaction effects23
Interaction terms with categorical dummies24
Plotting interactions through simple slope analysis24
Separate regressions27
Predicted values28
SPSS28
SAS28
Stata29
Adjusted predicted values30
Residuals31
Centering31
OLS regression in SPSS32
Example32
SPSS input32
SPSS Output33
The regression coefficient, b33
Interpreting b for dummy variables34
Confidence limits on b35
Beta weights35
Zero-order, partial, and part correlations36
R2 and the “Model Summary” table39
The Anova table40
Tolerance and VIF collinearity statistics40
SPSS plots41
SPSS “Plots” dialog41
Plot of standardized residuals against standardized predicted values43
Histogram of standardized residuals44
Normal probability (P-P) plot45
OLS regression in SAS46
Example46
SAS input47
SAS output48
The regression coefficient, b48
Interpreting b for dummy variables49
Confidence limits on b49
Beta weights50
Zero order, partial, and part correlation52
R-Squared and the Anova table53
Tolerance and VIF collinearity statistics54
SAS Plots55
SAS plotting options55
Plot of residuals against predicted values57
Histogram and kernel density plot of standardized residuals58
Normal probability (P-P) plot59
Normal quantile-quantile (Q-Q) plot60
Other SAS plots61
OLS regression in Stata64
Example64
Stata input65
Stata output66
The regression coefficient, b66
Interpreting b coefficients67
Confidence limits on b68
Beta weights68
R-Squared and the Anova table68
Zero order, partial, and part correlation69
Tolerance and VIF collinearity statistics69
Other Stata postestimation output70
Stata Plots71
Stata plotting options71
Plot of standardized residuals against standardized predicted values71
Histogram of standardized residuals73
Normal probability (P-P) plot74
Margin plots75
Robust regression75
Overview75
When to use robust regression76
Robust regression in SPSS76
Overview76
SPSS input77
SPSS output77
Robust regression in SAS78
SAS input78
SAS output80
Robust regression in Stata81
Stata input81
Stata output81
Hierarchical multiple regression82
Overview82
Examples83
Difference in differences regression83
Overview83
The parallel trend assumption84
Example data85
Data setup86
The model86
Difference modeling in SPSS89
SPSS input89
Should the dependent variable be linear or logarithmic?90
SPSS output92
Difference modeling in SAS94
SAS input94
Should the dependent variable be linear or logarithmic?95
SAS output96
Difference modeling in Stata98
Stata input98
Should the dependent variable be linear or logarithmic?98
Stata output99
Panel data regression101
Overview101
Types of panel data regression1
