See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/227467912

Econometric Methods with Applications in Business and

Economics

Book · January 2004

Source: RePEc

CITATIONS READS

162 8,420

5 authors, including:

Christiaan Heij Paul M.C. De Boer

Erasmus University Rotterdam Erasmus University Rotterdam
97 PUBLICATIONS   1,093 CITATIONS    56 PUBLICATIONS   480 CITATIONS   

SEE PROFILE SEE PROFILE

Herman Van Dijk

Erasmus University Rotterdam
228 PUBLICATIONS   3,336 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Empirical Vector Autoregressive Modeling View project

Article (2011) in : Journal of Economics, vol. 102, p. 217-235 View project

All content following this page was uploaded by Herman Van Dijk on 13 January 2016.

The user has requested enhancement of the downloaded file.

Econometric Methods with
Applications in Business
and Economics

Christiaan Heij
Paul de Boer
Philip Hans Franses
Teun Kloek
Herman K. van Dijk

OXFORD
UNIVERSITY PRESS
Detailed Contents

List of Exhibits xvi

Abbreviations xix
Guide to the Book xxi

Introduction 1

Econometrics 1
Purpose of the book 2
Characteristic features of the book 3
Target audience and required background knowledge 4
Brief contents of the book 4
Study advice 5
Teaching suggestions 6
Some possible course structures 8

1 Review of Statistics n

1.1 Descriptive statistics 12

1.1.1 Data graphs 12
1.1.2 Sample statistics 16
1.2 Random variables 20
1.2.1 Single random variables 20
1.2.2 Joint random variables 23
1.2.3 Probability distributions 29
1.2.4 Normal random samples 35
1.3 Parameter estimation 38
1.3.1 Estimation methods 38
1.3.2 Statistical properties 42
1.3.3 Asymptotic properties 47
1.4 Tests of hypotheses 55
1.4.1 Size and power 55
1.4.2 Tests for mean and variance 59
1.4.3 Interval estimates and the bootstrap 63
x Detailed Contents

Summary, further reading, and keywords 68

Exercises 71

2 Simple Regression 75

2.1 Least squares 76

2.1.1 Scatter diagrams 76
2.1.2 Least squares 79
2.1.3 Residuals and R2 82
2.1.4 Illustration: Bank Wages 84
2.2 Accuracy of least squares 87
2.2.1 Data generating processes 87
2.2.2 Examples of regression models 91
2.2.3 Seven assumptions 92
2.2.4 Statistical properties 94
2.2.5 Efficiency 97
2.3 Significance tests 99
2.3.1 Thet-test 99
2.3.2 Examples 101
2.3.3 Use under less strict conditions 103
2.4 Prediction 105
2.4.1 Point predictions and prediction intervals 105
2.4.2 Examples 107
Summary, further reading, and keywords 111
Exercises 113

3 Multiple Regression 117

3.1 Least squares in matrix form 118

3.1.1 Introduction 118
3.1.2 Least squares 120
3.1.3 Geometric interpretation 123
3.1.4 Statistical properties 125
3.1.5 Estimating the disturbance variance 127
3.1.6 Coefficient of determination 129
3.1.7 Illustration: Bank Wages 131
3.2 Adding or deleting variables 134
3.2.1 Restricted and unrestricted models 135
3.2.2 Interpretation of regression coefficients 139
3.2.3 Omitting variables 142
3.2.4 Consequences of redundant variables 143
3.2.5 Partial regression 145
 Detailed Contents xi

3.3 The accuracy of estimates 152

3.3.1 Thet-test 152
3.3.2 Illustration: Bank Wages 154
3.3.3 Multicollinearity 156
3.3.4 Illustration: Bank Wages 159

3.4 TheF-test 161

3.4.1 The F-test in different forms 161
3.4.2 Illustration: Bank Wages 166
3.4.3 Chow forecast test 169
3.4.4 Illustration: Bank Wages 174

Summary, further reading, and keywords 178

Exercises 180

4 Non-Linear Methods 187

4.1 Asymptotic analysis 188

4.1.1 Introduction 188
4.1.2 Stochastic regressors . 191
4.1.3 Consistency 193
4.1.4 Asymptotic normality 196
4.1.5 Simulation examples 198

4.2 Non-linear regression 202

4.2.1 Motivation 202
4.2.2 Non-linear least squares 205
4.2.3 Non-linear optimization 209
4.2.4 The Lagrange Multiplier test 212
4.2.5 Illustration: Coffee Sales 218

4.3 Maximum likelihood 222

4.3.1 Motivation 222
4.3.2 Maximum likelihood estimation 224
4.3.3 Asymptotic properties 228
4.3.4 The Likelihood Ratio test 230
4.3.5 The Wald test 232
4.3.6 The Lagrange Multiplier test 235
4.3.7 LM-test in the linear model 238
4.3.8 Remarks on tests 240
4.3.9 Two examples 243

4.4 Generalized method of moments 250

4.4.1 Motivation 250
4.4.2 GMM estimation 252
4.4.3 GMM standard errors 255
4.4.4 Quasi-maximum likelihood 259
xii Detailed Contents

4.4.5 GMM in simple regression 260

4.4.6 Illustration: Stock Market Returns 262
Summary, further reading, and keywords 266
Exercises 268

5 Diagnostic Tests and Model Adjustments 273

5.1 Introduction 274

5.2 Functional form and explanatory variables 277
5.2.1 The number of explanatory variables 277
5.2.2 Non-linear functional forms 285
5.2.3 Non-parametric estimation 289
5.2.4 Data transformations 296
5.2.5 Summary 302
5.3 Varying parameters 303
5.3.1 The use of dummy variables 303
5.3.2 Recursive least squares 310
5.3.3 Tests for varying parameters 313
5.3.4 Summary 318
5.4 Heteroskedasticity 320
5.4.1 Introduction 320
5.4.2 Properties of OLS and White standard errors 324
5.4.3 Weighted least squares 327
5.4.4 Estimation by maximum likelihood and feasible WLS 334
5.4.5 Tests for homoskedasticity 343
5.4.6 Summary 352
5.5 Serial correlation 354
5.5.1 Introduction 354
5.5.2 Properties of OLS 358
5.5.3 Tests for serial correlation 361
5.5.4 Model adjustments 368
5.5.5 Summary 376
5.6 Disturbance distribution 378
5.6.1 Introduction 378
5.6.2 Regression diagnostics 379
5.6.3 Test for normality 386
5.6.4 Robust estimation 388
5.6.5 Summary 394
5.7 Endogenous regressors and instrumental variables 396
5.7.1 Instrumental variables and two-stage least squares 396
5.7.2 Statistical properties of IV estimators 404
5.7.3 Tests for exogeneity and validity of instruments 409
5.7.4 Summary 418
 Detailed Contents xiii

5.8 Illustration: Salaries of top managers 419

Summary, further reading, and keywords 424

Exercises 427

6 Qualitative and Limited Dependent Variables 437

6.1 Binary response 438

6.1.1 Model formulation 438
6.1.2 Probit and logit models 443
6.1.3 Estimation and evaluation 447
6.1.4 Diagnostics 452
6.1.5 Model for grouped data 459
6.1.6 Summary 461

6.2 Multinomial data 463

6.2.1 Unordered response 463
6.2.2 Multinomial and conditional logit 466
6.2.3 Ordered response 474
6.2.4 Summary 480

6.3 Limited dependent variables 482

6.3.1 Truncated samples 482
6.3.2 Censored data 490
6.3.3 Models for selection and treatment effects 500
6.3.4 Duration models 511
6.3.5 Summary 521

Summary, further reading, and keywords 523

Exercises 525

7 Time Series and Dynamic Models 531

7.1 Models for stationary time series 532

7.1.1 Introduction 532
7.1.2 Stationary processes 535
7.1.3 Autoregressive models 538
7.1.4 ARMA models 542
7.1.5 Autocorrelations and partial autocorrelations 545
7.1.6 Forecasting 550
7.1.7 Summary 553

7.2 Model estimation and selection 555

7.2.1 The modelling process • 555
7.2.2 Parameter estimation 558
7.2.3 Model selection 563
xiv Detailed Contents

7.2.4 Diagnostic tests 567

7.2.5 Summary 576
7.3 Trends and seasonals 578
7.3.1 Trend models 578
7.3.2 Trend estimation and forecasting 585
7.3.3 Unit root tests 592
7.3.4 Seasonality 604
7.3.5 Summary 611
7.4 Non-linearities and time-varying volatility 612
7.4.1 Outliers 612
7.4.2 Time-varying parameters 616
7.4.3 GARCH models for clustered volatility 620
7.4.4 Estimation and diagnostic tests of GARCH models 626
7.4.5 Summary 636
7.5 Regression models with lags 637
7.5.1 Autoregressive models with distributed lags 637
7.5.2 Estimation, testing, and forecasting 640
7.5.3 Regression of variables with trends 647
7.5.4 Summary 654
7.6 Vector autoregressive models 656
7.6.1 Stationary vector autoregressions 656
7.6.2 Estimation and diagnostic tests of stationary VAR models 661
7.6.3 Trends and cointegration 667
7.6.4 Summary 681
7.7 Other multiple equation models 682
7.7.1 Introduction 682
7.7.2 Seemingly unrelated regression model 684
7.7.3 Panel data 692
7.7.4 Simultaneous equation model 700
7.7.5 Summary 709
Summary, further reading, and keywords 710
Exercises 713

Appendix A. Matrix Methods 723

A.1 Summations 723

A.2 Vectors and matrices 725
A.3 Matrix addition and multiplication 727
A.4 Transpose, trace, and inverse 729
A.5 Determinant, rank, and eigenvalues 731
A.6 Positive (semi)definite matrices and projections 736
A.7 Optimization of a function of several variables 738
 Detailed Contents xv

A.8 Concentration and the Lagrange method 743

Exercise 746

Appendix B. Data Sets 747

List of Data Sets 748

Index 773

View publication stats