Contents
1 The Nature of Econometrics
1.1 Economic models and econometric models
1.2 Types of economic data
1.3 Describing a bivariate relationship
1.4 The conditional expectation function
1.5 The software workflow
1.6 Practice Problems
2 The Two-Variable Linear Model
2.1 The model and its assumptions
2.2 Least squares
2.3 Properties of the least squares estimators
2.4 Inference
2.5 Prediction
2.6 Regression in software
2.7 Practice Problems
3 Functional Form
3.1 Time as a regressor
3.2 Constant growth curves
3.3 Transformations of the variables
3.4 The logistic curve
3.5 Choosing the functional form
3.6 Functional form in software
3.7 Practice Problems
4 Large-Sample Theory and the Autoregressive Equation
4.1 Why exact theory breaks down
4.2 Convergence in probability
4.3 Convergence in distribution
4.4 Least squares in large samples
4.5 The autoregressive scheme
4.6 Maximum likelihood for the autoregressive equation
4.7 Large samples in software
4.8 Practice Problems
5 Matrix Algebra and Quadratic Forms
5.1 Matrix results
5.2 Random vectors
5.3 The multivariate normal distribution
5.4 Distributions of quadratic forms
5.5 Application: the residuals of a regression
5.6 Matrices in software
5.7 Practice Problems
6 The \(k\)-Variable Linear Model
6.1 The model in matrix form
6.2 Least squares
6.3 The decomposition of the sum of squares and \(R^2\)
6.4 Partitioned regression: the Frisch–Waugh–Lovell theorem
6.5 Partial correlation
6.6 The geometry of least squares
6.7 Multiple regression in software
6.8 Practice Problems
7 Inference in the \(k\)-Variable Model
7.1 The sampling distribution of \(b\)
7.2 The Gauss–Markov theorem
7.3 Testing linear restrictions
7.4 Restricted least squares and the \(F\) test
7.5 Confidence intervals and regions
7.6 Prediction
7.7 Testing in software
7.8 Practice Problems
8 Specification Error and Structural Change
8.1 Omitted and irrelevant variables
8.2 The Chow forecast test
8.3 The Chow test of structural change
8.4 Dummy variables
8.5 Recursive residuals and the CUSUM test
8.6 Testing functional form: RESET
8.7 Specification tests in software
8.8 Practice Problems
9 Maximum Likelihood and Generalised Least Squares
9.1 The likelihood principle
9.2 Maximum likelihood in the linear model
9.3 The likelihood ratio, Wald and Lagrange multiplier tests
9.4 Non-spherical disturbances and generalised least squares
9.5 Maximum likelihood and GLS in software
9.6 Practice Problems
10 Heteroscedasticity
10.1 Consequences for least squares
10.2 Heteroscedasticity-robust standard errors
10.3 Testing for heteroscedasticity
10.4 Estimation under heteroscedasticity
10.5 Heteroscedasticity in software
10.6 Practice Problems
11 Autocorrelation and ARCH
11.1 Autocorrelated disturbances
11.2 Consequences for least squares
11.3 Testing for autocorrelation
11.4 Estimation with autocorrelated disturbances
11.5 Forecasting with autocorrelated disturbances
11.6 Autoregressive conditional heteroscedasticity
11.7 Autocorrelation in software
11.8 Practice Problems
12 Unit Roots, Cointegration and Error Correction
12.1 Stationary and integrated processes
12.2 Spurious regression and the asymptotics of a unit root
12.3 Unit root tests
12.4 Cointegration
12.5 Error correction models
12.6 Unit roots and cointegration in software
12.7 Practice Problems
13 Instrumental Variables
13.1 Endogenous regressors
13.2 The instrumental variables estimator
13.3 Two-stage least squares
13.4 Testing endogeneity and instrument validity
13.5 Instrumental variables in software
13.6 Practice Problems
14 Simultaneous Equations, SUR and Vector Autoregressions
14.1 Structural and reduced forms
14.2 Identification
14.3 Estimating a system
14.4 Seemingly unrelated regressions
14.5 Vector autoregressions
14.6 Cointegrated systems: the vector error correction model
14.7 Systems in software
14.8 Practice Problems
15 The Generalised Method of Moments
15.1 The method of moments
15.2 The generalised method of moments
15.3 Linear GMM and its relation to 2SLS
15.4 Testing overidentifying restrictions
15.5 Applications and practical issues
15.6 GMM in software
15.7 Practice Problems
16 Panel Data
16.1 Unobserved heterogeneity
16.2 Fixed effects
16.3 Random effects
16.4 Choosing between fixed and random effects
16.5 Cluster-robust standard errors
16.6 Dynamic panels
16.7 Panel data in software
16.8 Practice Problems
17 Limited Dependent Variables
17.1 Binary choice
17.2 Censored data: the Tobit model
17.3 Sample selection
17.4 Count data
17.5 Limited dependent variables in software
17.6 Practice Problems
18 Review and Synthesis
18.1 A map of the methods
18.2 When the assumptions fail
18.3 Review problems
References
References