1. Introducing Econometrics.
Learning Objectives
1.1 The role of this chapter and the nature of this book.
1.2 Question 1: So What Is Econometrics?
1.3 Question 2: Who uses Econometrics and Why?
1.4 Question 3: Do You Have to be an econometrician to be do econometrics?
1.5 Question 4: Do users of econometrics disagree?
1.6 Question 5: Could we do without econometrics?
1.7 Question 6: How did modern econometrics start?
1.8 Question 7: Where is econometrics going to?
1.9 Question 8: How do I use this book?
1.10 Question 9: What should I know and be able to do when I have finished?
1.11 Question 10: What Software Should I Use do Econometrics?
1.12 What Comes Next?
Do's and Don'ts
Exercises
References2. Statistical Testing and Modelling. The Basics.
Learning Objectives
2.1 Types of data.
2.2 Sampling
2.3 The uses of the concept of probability.
2.4 Hypothesis testing and probability distributions.
2.5 Hypothesis testing: how to write it down properly.
2.6 How do we decide on the significance level.
2.7 Covariance and correlation coefficients.
2.8 Conclusion
Do's and Don'ts
Exercises
References3. The Classical Linear Regression Model Introduced.
Learning Objectives
3.1 Bivariate Regression.
3.2 The role of the disturbance term.
3.3 Classical assumptions of the disturbance term.
3.4 OLS estimators: what makes them blue and where do they come from.
3.5 Hypothesis Testing in the CLRM.
3.6 A note on the R2 statistic.
3.7 What is the Gauss-Markov Theorem?
3.8 Examples of bivariate regression.
3.9 From bivariate to multiple regression.
3.10 Review of published studies.
3.11 Conclusion
Do's and Don'ts
Exercises
References4. Preparing and Using Data.
Learning Objectives
4.1 Introduction
4.2 Possible Problems with the data set.
4.3 How will my data arrive and what do I do with it?
4.4 Descriptive Exploration of Your Data.
4.5 Running a Regression.
4.6 Interpreting your results.
4.7 Additional Treatment of your regression output.
4.8 Turning your regression output into a presentation or article.
4.9 Case Study. The Willingness to Pay Study.
4.10 Collecting data: some further reflections.
4.11 Conclusion
Do's and Don'ts
Exercises
References
Appendix: Questionnaire Design5. What do all these tests and statistics mean?
Learning Objectives
5.1 Introduction. Typical test statistics in computer output.
5.2 Telling the story of the regression coefficients: the use of elasticities.
5.3 The construction and use of ‘F’ tests in regression.
5.4 Adjusting the R squared: how and why?
5.5 Be careful with all R squareds.
5.6 Basic Econometric Forecasting.
5.7 Review Studies.
5.8 Conclusion
Do's and Don'ts
Exercises
References 6. Making Regression Analysis More Useful I: Transformations
Learning Objectives
6.1 Introduction
6.2 Non-Linearity as a problem.
6.3 Making interaction terms.
6.4 What if we wrongly choose a linear model?
6.5 How do we estimate non-linear equations using OLS?
6.6 Choice of functional form and a word on R2.
6.7 Some other transformations for non-linearity.
6.8 Lag and lead transformations to produce dynamic models.
6.9 Review Studies.
6.10 Conclusion
Do's and Don'ts
Exercises
References 7. Making Regression Analysis More Useful II: Dummies and Trends
Learning Objectives
7.1 Introduction: making a dummy.
7.2 Why do we use dummies?
7.3 Are Dummies always 0-1 Variables?
7.4 Where do I get my dummies from? The seasons are an obvious answer.
7.5 The slope dummy.
7.6 Review Studies.
7.7 Another use for dummies: forecast evaluations.
7.8 Time trends.
7.9 Another use for dummies: spline functions to produce non-linearity.
7.10 Conclusion
Do's and Don'ts
Exercises
Study Questions
References 8. Predicting and Explaining Discrete Events: Logit and Probit Models
Learning Objectives
8.1 Introduction
8.2 Predicting Probabilities Using OLS.
8.3 Should We Use OLS to explain probabilities:? The Alternatives.
8.4 The Rationale for Logit and Probit Models.
8.5 Basic Use and Interpretation of Logit and Probit Models.
8.6 Review Studies.
8.7 More Complex Probabilistic Models.
8.8 Problems in Interpreting and Testing Logit and Probit Models.
8.9 Conclusion
Do's and Don'ts
Exercises
References 9. More Tests: Diagnosing the results of basic models.
Learning Objectives
9.1 Introduction
9.2 Testing for Outliers.
9.3 Testing for Normality.
9.4 Testing for Stability.
9.5 Testing for Functional Form.
9.6 Testing for Heteroscedasticity.
9.7 Testing for Autocorrelation.
9.8 Testing for Bias.
9.9 Review Studies.
9.10 Conclusion
Do's and Don'ts
Exercises
References10. Multicollinearity. Serious Worry or Minor Nuisance?
Learning Objectives
10.1 Introduction
10.2 What is Multicollinearity?
10.3 Consequences of Multicollinearity.
10.4 Exploring for Multicollinearity.
10.5 A Proposed Test for Multicollinearity.
10.6 Causes of Multicollinearity.
10.7 Should I Worry About Multicollinearity Or Not?
10.8 Review Studies.
10.9 Conclusion
Do's and Don'ts
Exercises
References11. Problem Solving: Heteroscedasticity.
Learning Objectives
11.1 Introduction
11.2 Consequences of Heteroscedasticity.
11.3 Solving the problem of hetroscedasticity: I. Use Transformed Data To Obtain
Weighted Least Squares (WLS) estimates.
11.4 Solving the problem of heteroscedascity:II. Use Corrected Standard Errors.
11.5 Causes of Heteroscedasticity.
11.6 Should I correct for heteroscedasicity?
11.7 Review Studies.
11.8 Conclusion
Do's and Don'ts
Exercises
References 12. Multiple equation models: Specification and the Identification Problem.
Learning Objectives
12.1 Introduction
12.2 Do we need more than one equation in our model?
12.3 Handling systems of equations.
12.4 Identification : the order condition.
12.5 Rules for identification continued: order conditions n a larger model.
12.6 Some Important Questions.
12.7 Conclusion
Do's and Don'ts
Exercises
References 13. Multiple equation models: Methods of Estimation.
Learning Objectives
13.1 Introduction- Identification Again.
13.2 Using OLS to estimate a multiple equation model: the bias problem.
13.3 2SLS: modified OLS.
13.4 The Relationship Between 2SLS and IV.
13.5 Interpretation of the results of 2SLS/IV estimates: some examples.
13.6 Exogeneity Testing.
13.7 Review Studies.
13.8 Other types of systems model: SUR estimation and Path Models.
13.9 More advanced methods I: 3SLS.
13.10 More advanced methods II: FIML.
13.11 Can we test for identification?
13.12 A recap: Four Problems.
13.13 Conclusion
Do's and Don'ts
Exercises
References 14. Problem Solving: Time-Series.
Learning Objectives
14.1 Introduction
14.2 What we already know about time series.
14,3 The problem of Spurious Regression.
14.4 Avoiding spurious regression: pre testing I; unit roots and other tests.
14.5 Cointegration: definition and tesing.
14.6 Formulating a time-series econometrics model: Engle-Granger Two Step Model.
14.7 Review Studies.
14.8 Some reservations on the above methods.
14.9 Granger Causality.
14.10 Time series analysis as opposed to (structural) economic analysis of time series.
14.11 More sophisticated approaches to cointegration testing and system modeling.
14.12 Conclusion
Do's and Don'ts
Exercises
References 15. Conclusion.
Learning Objectives
15.1 Introduction: Time to review the subject field of econometrics. Data and technique.
15.2 Chapter 1 Revisited: Methodology: Bayesian Econometrics.
15.3 Chapter 2 Revisited: The significance of significance testing.
15.4 Chapter 3 Revisited: The basic regression equation. Are Single equation Models of Any Use?
15.5 Chapter 4 Revisited: Measurement.
15.6 Chapter 5 revisited: Goodness of Fit; Model Selection Tests.
15.7 Chapter 6 Revisited: Simple Dynamic Models and Non-Linearity.
15.8 Chapter 7 Revisited: Are artificial variable safe to play with?
15.9 Chapter 8 Revisited: Limited dependent variable models.
15.10 Chapter 9 The Reliability of Diagnostic Tests.
15.11 Chapter 10 Revisited : Multicollinearity.
15.12 Chapter 11 Revisited: Heteroscedasticity.
15.13 Chapter 12 Revisited : Identification.
15.14 Chapter 13 Revisited: Systems of Equations.
15.15 Chapter 14 Revisited : Time series Analysis.
15.16 Final Words - What Use is Econometrics?
Exercises
Further Reading Appendices
I. Blank Template of Summary Sheet for Review Studies.
II. Brief Description of the Excel files of Data Sets.
III. The Notion of Causality.