Preface                                            xv
Acknowledgments                                    xix
A personal message from the author                 xxi
        List of tables                             xxiii
        List of figures                            xxvii
  Part I The linear regression model               1    (66)
    Chapter 1 The linear regression model: an      2    (23)
    overview
      1.1 The linear regression model              2    (3)
      1.2 The nature and sources of data           5    (1)
      1.3 Estimation of the linear regression      6    (2)
      model
      1.4 The classical linear regression model    8    (2)
      (CLRM)
      1.5 Variances and standard errors of OLS     10   (1)
      estimators
      1.6 Testing hypotheses about the true or     11   (2)
      population regression coefficients
      1.7 R2: a measure of goodness of fit of      13   (1)
      the estimated regression
      1.8 An illustrative example: the             14   (5)
      determinants of hourly wages
      1.9 Forecasting                              19   (1)
      1.10 The road ahead                          19   (6)
        Exercise                                   21   (1)
        Appendix: The method of maximum            22   (3)
        likelihood
    Chapter 2 Functional forms of regression       25   (22)
    models
      2.1 Log-linear, double-log, or constant      25   (4)
      elasticity models
      2.2 Testing validity of linear               29   (1)
      restrictions
      2.3 Log-lin or growth models                 30   (4)
      2.4 Lin-log models                           34   (2)
      2.5 Reciprocal models                        36   (1)
      2.6 Polynomial regression models             37   (3)
      2.7 Choice of the functional form            40   (1)
      2.8 Comparing linear and log-linear models   40   (1)
      2.9 Regression on standardized variables     41   (2)
      2.10 Measures of goodness of fit             43   (2)
      2.11 Summary and conclusions                 45   (2)
        Exercises                                  45   (2)
    Chapter 3 Qualitative explanatory variables    47   (20)
    regression models
      3.1 Wage function revisited                  47   (2)
      3.2 Refinement of the wage function          49   (1)
      3.3 Another refinement of the wage           50   (3)
      function
      3.4 Functional form of the wage regression   53   (2)
      3.5 Use of dummy variables in structural     55   (3)
      change
      3.6 Use of dummy variables in seasonal       58   (3)
      data
      3.7 Expanded sales function                  61   (3)
      3.8 Summary and conclusions                  64   (3)
        Exercises                                  65   (2)
  Part II Critical evaluation of the classical     67   (74)
  linear regression model
    Chapter 4 Regression diagnostic I:             68   (14)
    multicollinearity
      4.1 Consequences of imperfect                69   (2)
      collinearitys
      4.2 An example: married women's hours of     71   (1)
      work in the labor market
      4.3 Detection of multicollinearity           71   (3)
      4.4 Remedial measures                        74   (2)
      4.5 The method of principal components       76   (2)
      (PC)
      4.6 Summary and conclusions                  78   (4)
        Exercises                                  79   (3)
    Chapter 5 Regression diagnostic II:            82   (15)
    heteroscedasticity
      5.1 Consequences of heteroscedasticity       82   (1)
      5.2 Abortion rates in the USA                83   (3)
      5.3 Detection of heteroscedasticity          86   (3)
      5.4 Remedial measures                        89   (5)
      5.5 Summary and conclusions                  94   (3)
        Exercises                                  96   (1)
    Chapter 6 Regression diagnostic III:           97   (17)
    autocorrelation
      6.1 US consumption function, 1947--2000      97   (2)
      6.2 Tests of autocorrelation                 99   (5)
      6.3 Remedial measures                        104  (5)
      6.4 Model evaluation                         109  (3)
      6.5 Summary and conclusions                  112  (2)
        Exercises                                  113  (1)
    Chapter 7 Regression diagnostic IV: model      114  (27)
    specification errors
      7.1 Omission of relevant variables           114  (4)
      7.2 Tests of omitted variables               118  (3)
      7.3 Inclusion of irrelevant or               121  (1)
      unnecessary variables
      7.4 Misspecification of the functional       122  (2)
      form of a regression model
      7.5 Errors of measurement                    124  (1)
      7.6 Outliers, leverage and influence data    125  (3)
      7.7 Probability distribution of the error    128  (1)
      term
      7.8 Random or stochastic regresssors         129  (1)
      7.9 The simultaneity problem                 130  (5)
      7.10 Summary and conclusions                 135  (6)
        Exercises                                  136  (2)
        Appendix: Inconsistency of the OLS         138  (3)
        estimators of the consumption function
  Part III Regression models with                  141  (64)
  cross-sectional data
    Chapter 8 The logit and probit models          142  (14)
      8.1 An illustrative example: to smoke or     142  (1)
      not to smoke
      8.2 The linear probability model (LPM)       143  (1)
      8.3 The logit model                          144  (7)
      8.4 The probit model                         151  (2)
      8.5 Summary and conclusions                  153  (3)
        Exercises                                  154  (2)
    Chapter 9 Multinomial regression models        156  (14)
      9.1 The nature of multinomial regression     156  (2)
      models
      9.2 Multinomial logit model (MLM): school    158  (6)
      choice
      9.3 Conditional logit model (CLM)            164  (3)
      9.4 Mixed logit (MXL)                        167  (1)
      9.5 Summary and conclusions                  167  (3)
        Exercises                                  169  (1)
    Chapter 10 Ordinal regression models           170  (11)
      10.1 Ordered multinomial models (OMM)        171  (1)
      10.2 Estimation of ordered logit model       171  (2)
      (OLM)
      10.3 An illustrative example: attitudes      173  (3)
      towards working mothers
      10.4 Limitation of the proportional odds     176  (3)
      model
      10.5 Summary and conclusions                 179  (2)
        Exercises                                  180  (1)
        Appendix: Derivation of Eq. (10.4)         180  (1)
    Chapter 11 Limited dependent variable          181  (12)
    regression models
      11.1 Censored regression models              182  (3)
      11.2 Maximum-likelihood (ML) estimation      185  (4)
      of the censored regression model: the
      Tobit model
      11.3 Truncated sample regression models      189  (2)
      11.4 Summary and conclusions                 191  (2)
        Exercises                                  191  (2)
    Chapter 12 Modeling count data: the Poisson    193  (12)
    and negative binomial regression models
      12.1 An illustrative example                 193  (3)
      12.2 The Poisson regression model (PRM)      196  (3)
      12.3 Limitation of the Poisson regression    199  (3)
      model
      12.4 The negative binomial regression        202  (1)
      model
      12.5 Summary and conclusions                 202  (3)
        Exercises                                  203  (2)
  Part IV Topics in time series econometrics       205  (135)
    Chapter 13 Stationary and nonstationary        206  (18)
    time series
      13.1 Are exchange rates stationary?          206  (1)
      13.2 The importance of stationary time       207  (1)
      series
      13.3 Tests of stationarity                   208  (3)
      13.4 The unit root test of stationarity      211  (4)
      13.5 Trend stationary vs. difference         215  (3)
      stationary time series
      13.6 The random walk model (RWM)             218  (4)
      13.7 Summary and conclusions                 222  (2)
        Exercises                                  223  (1)
    Chapter 14 Cointegration and error             224  (14)
    correction models
      14.1 The phenomenon of spurious regression   224  (1)
      14.2 Simulation of spurious regression       225  (1)
      14.3 Is the regression of consumption        226  (3)
      expenditure on disposable income spurious?
      14.4 When a spurious regression may not      229  (1)
      be spurious
      14.5 Tests of cointegration                  230  (1)
      14.6 Cointegration and error correction      231  (2)
      mechanism (ECM)
      14.7 Are 3-month and 6-month Treasury        233  (3)
      Bills cointegrated?
      14.8 Summary and conclusions                 236  (2)
        Exercises                                  237  (1)
    Chapter 15 Asset price volatility: the ARCH    238  (13)
    and GARCH models
      15.1 The ARCH model                          239  (6)
      15.2 The GARCH model                         245  (2)
      15.3 Further extensions of the ARCH model    247  (2)
      15.4 Summary and conclusions                 249  (2)
        Exercise                                   250  (1)
    Chapter 16 Economic forecasting                251  (28)
      16.1 Forecasting with regression models      252  (5)
      16.2 The Box--Jenkins methodology: ARIMA     257  (2)
      modeling
      16.3 An ARM A model of IBM daily closing     259  (6)
      prices, 3 January 2000 to 31 October 2002
      16.4 Vector autoregression (VAR)             265  (5)
      16.5 Testing causality using VAR: the        270  (4)
      Granger causality test
      16.6 Summary and conclusions                 274  (5)
        Exercises                                  276  (3)
    Chapter 17 Panel data regression models        279  (17)
      17.1 The importance of panel data            279  (1)
      17.2 An illustrative example: charitable     280  (1)
      giving
      17.3 Pooled OLS regression of charity        281  (2)
      function
      17.4 The fixed effects least squares         283  (2)
      dummy variable (LSDV) model
      17.5 Limitations of the fixed effects        285  (1)
      LSDV model
      17.6 The fixed effect within group (WG)      286  (2)
      estimator
      17.7 The random effects model (REM) or       288  (1)
      error components model (ECM)
      17.8 Fixed effects model vs. random          289  (3)
      effects model
      17.9 Properties of various estimators        292  (1)
      17.10 Panel data regressions: some           292  (1)
      concluding comments
      17.11 Summary and conclusions                293  (3)
        Exercises                                  294  (2)
    Chapter 18 Survival analysis                   296  (13)
      18.1 An illustrative example: modeling       296  (1)
      recidivism duration
      18.2 Terminology of survival analysis        297  (3)
      18.3 Modeling recidivism duration            300  (1)
      18.4 Exponential probability distribution    300  (3)
      18.5 Weibull probability distribution        303  (2)
      18.6 The proportional hazard model           305  (2)
      18.7 Summary and conclusions                 307  (2)
        Exercises                                  308  (1)
    Chapter 19 Stochastic regressors and the       309  (31)
    method of instrumental variables
      19.1 The problem of endogeneity              310  (2)
      19.2 The problem with stochastic             312  (2)
      regressors
      19.3 Reasons for correlation between         314  (4)
      regressors and the error term
      19.4 The method of instrumental variables    318  (3)
      19.5 Monte Carlo simulation of IV            321  (1)
      19.6 Some illustrative examples              322  (2)
      19.7 A numerical example: earnings and       324  (4)
      educational attainment of youth in the USA
      19.8 Hypothesis testing under IV             328  (2)
      estimation
      19.9 Test of endogeneity of a regressor      330  (1)
      19.10 How to find whether an instrument      331  (1)
      is weak or strong
      19.11 The case of multiple instruments       332  (3)
      19.12 Regression involving more than one     335  (2)
      endogenous regressor
      19.13 Summary and conclusions                337  (3)
        Exercises                                  338  (2)
  Appendices
      1 Data sets used in the text                 340  (6)
      2 Statistical appendix                       346  (20)
Index                                              366