1 Introduction to the Regression Model

1.1 Curve fitting
1.2 Derivation of least squares
Appendix 1.1 The Use of Summation Operators
Appendix 1.2 Derivation of Least-Squares Parameter
Estimates

2 Elementary Statistics: A Review

2.1 Random Variables
2.2 Estimation
2.3 Desirable properties of estimators
2.4 Probability distribution
2.5 Hypothesis testing and confidence intervals
2.6 Descriptive statistics
Appendix 2.1 The properties of the expectations operator
Appendix 2.2 Maximum-Likelihood estimation

3 The Two-Variable Regression Model

3.1 The model
3.2 Best linear unbiased estimation
3.3 Hypothesisn testing and confidence intervals
3.4 Analysis of variance and correlation
Appendix 3.1 Variance of the Least-Squares Slope
Appendix 3.2 Some Properties of the Least-Squares residuals

4 The Multiple Regression Model

4.1 The model
4.2 Regression statistics
4.3 F tests ,R2, and corrected R2
4.4 Multicollinearity
4.5 Standardized coefficient and elasticites
4.6 Partial correlation and stepwisw regression
Appendix 4.1 Least-Squares Parameter Estimation
Appendix 4.2 Regression Coefficients
Appendix 4.3 The Multiple Regression Model in Matrix

Part 2 Single-Equation Regression Models

5 Using the Multiple Regression Model

5.1 The general linear model
5.2 Use of dummy variables
5.3 The use of t and f tests for hypothesis involving more than one parameter
5.4 Piecewise linear regression
5.5 The multiple regression model with stochastic explanatory variables
Appendix 5.1 Tests Involving Dummy-Variable Coefficients

6 Serial Correlation and Heteroscedasticity

6.1 Heteroscedasticity
6.2 Serial correlation
Appendix 6.1 Generalized Least-Squares Estimation

7 Instrumental Variables and Model Specification

7.1 Correlation between an independent variable and the error term
7.2 Errors in varibles
7.3 Specification error
7.4 Regression diagnostics
7.5 Specification tests
Appendix 7.1 Instrumental-Variables Estimation in Matrix

8 Forecasting with a Single-Equation Regression Model

8.1 Unconditional forecasting
8.2 Forecasting with serially correlated errors
8.3 Conditional forecasting
Appendix 8.1 Forecasting with the multiple regression model

9 Single-Equation Estimation: Advanced Topics

9.1 Distributed lag models
9.2 Tests for causality
9.3 Missing observations
9.4 The use of panel data
Appendix 9.1 Estimating Confidence Intervals for Long-Run Elasticities

10 Nonlinear and Maximum-Likelihood Estimation

10.1 Nonlinear estimation
10.2 Maximum-likeihood estimation
10.3 ARCH and GARCH models
Appendix 10.1 Generalized Method of Moments Estimation

11 Models of Qualitative Choice

11.1 Binary-Choice models
11.2 Multiple-Choice models
11.3 Censored regression models
Appendix 11.1 Maximum-Likelihood Estimation of the Logit and Probit Models

Part 3 Multi-Equation Models

12 Simultaneous-Equation Estimation

12.1 Introduction to simultaneous-equation models
12.2 The identification problem
12.3 Consistent parameter estimation
12.4 Two-stage least squares
12.5 Simultaneous-equation estimation with serial correlation and lagged dependent variables
12.6 More advanced estimation methods
Appendix 12.1 The Identification Problem in Matrix Form
Appendix 12.2 Two-Stage Least Squares in Matrix Form
Appendix 12.3 Seemingly Unrelated Regression Estimation in Matrix Form

13 Introduction to Simulation Models

13.1 The simulation process
13.2 Evaluating simulation models
13.3 A simulation example
13.4 Model estimation
13.5 Nonstructural models: vector autoregressions
13.6 Modeling with limited data

14 Dynamic Behavior of Simulation Models

14.1 Model behaviour: stability and oscillations
14.2 Model behaviour: multipliers and dynamic response
14.3 The impulse response function and vector autoregression
14.4 Adjusting simulation models
14.5 Stochastic simulation
Appendix 14.1 A Small Macroeconomic Model

Part 4 Time-Series Models

15 Smoothing and Extrapolation of Time Series

15.1 Simple extrapolation models
15.2 Smoothing and seasonal adjustment

16 Properties of Stochastic Time Series

16.1 Introduction to stochastic time-series models
16.2 Characterizing time series: the autocorrelation function
16.3 Testing for random walks
16.4 Co-Integrated times series
Appendix 16.1 The autocorrelation function for a stationary process

17 Linear Time-Series Models

17.1 Moving average models
17.2 Autoregressive models
17.3 Mixed autoregressive-moving average models
17.4 Homogeneous nonstationary processes: ARIMA models
17.5 Specification of ARIMA models
Appendix 17.1 Stationarity, Invertibility, and Homogeneity

18 Estimating and Forecasting with Time-Series Models

18.1 Model estimation
18.2 Diagnostic checking
18.3 Minimum mean-square-error forecasts
18.4 Computing a forecast
18.5 The forecast error
18.6 Forecasts confidence intervals
18.7 Properties of ARIMA forecasts
18.8 Two examples

19 Applications of Time-Series Models

19.1 Reviews of the modeling process
19.2 Models of economic variables: inventory investment
19.3 Forecasting seasonal telephone data
19.4 Combining regression analysis with a time-series model: transfer function models
19.5 A combined regression-time-series model to forecast short-tem saving deposit flows
19.6 A combined regression-time-series models to forecast interest rates

Solutions to selected problems
Indexes
Author Index
Subject Index