Econ/ARE 240D Syllabus

**Instructor:**

Professor Colin Cameron

SSH Building 1124 (530) 564-0630

accameron@ucdavis.edu

**Meeting:**

Tues Thurs** **10.00 – 11.50 a.m. Wickson 1038

**Office Hours:**

Tuesday afternoon 3.00 - 5.00 p.m.

Thursday morning 9.00 a.m. – 9.50 a.m.

**Teaching Assistant:
**Lucas
Herrenbrueck Herrenbrueck@ucdavis.edu

Office Hours: Wednesday 9.30 - 11.30 a.m.

**Course Goals:** (1) To be able to perform estimation and
testing in
non-linear cross-section regression models, (2) to be sufficiently
comfortable with asymptotic theory for nonlinear models to be able
to
read econometrics articles in journals such as Econometrica and
Journal
of Econometrics, (3) to be able to implement cross-section methods
as
needed for Ph.D. thesis.

**Pre-requisites:** The listed pre-requisite is Econ / Ag Econ
240B.

The essential pre-requisite is a good understanding of the linear
regression model with matrix algebra.

**Course Outline:**

Class 1 | 0.5 class | Introduction: Linear Models |

CT: 4.4-4.5. Gr: 3.2, 5.2. W: 4.2. | ||

Class 2 | 1.5 classes | Introduction: Review of Asymptotic Theory |

CT: Appx.A. Am: 3. Gr: AppxD. W: 3.1-3.4 | ||

Classes 3-4 |
2 classes | Estimation: Extremum and M-estimators |

CT: 5.2-5.5 Am: 4.1. Gr: 16.5. W: 12.1-12.3 | ||

Class 5 | 1 class | Estimation: Iterative Methods for Computation |

CT: 10.2-10.3. Am: 4.4. Gr: AppxE W: 12.7. | ||

Class 6-7 |
1 class | Estimation: ML and NLS |

CT: 5.6-5.8 Am: 4.3 Gr: 9.2, 21.1-4 W: 12.4, 13.1-5 | ||

Class 8-9, 11-12 | 4 classes | Models: Logit and probit (binary and multinomial outcomes) |

CT: 14.1-14.4, 15.1-15.5, 15.9.
Am: 9.1-9.3. Gr: 21.1-21.8. Mad: 2-3. W: 15.1-15.6, 15.9-15.10. |
||

Class 10 | 1 class | Midterm Exam. |

Class 13-14 | 2 classes | Models: Tobit |

CT: 16.1-16.6. Am: 10.1-10.7. Gr: 22.1-22.4. Mad: 6.1-6.6, 8.1-8.5. W: 16.1-16.6 |
||

Class 15 | 1 class | Estimation: GMM |

CT: 6.1-6.5. Gr
18.1-18.3.
W: 14.1-14.2 |
||

Class 16 | 1 class | Testing, bootstrap methods |

CT: 7.1-7.4, 8.2-8.3. Gr: 17.5,
AppxE.4. W: 12.6, 13.6. |
||

Class 17-20 | 4 classes | Panel data |

CT: 21.1-21.8. Am: 6.4,
6.6-6.8. Gr: 13.1-13.4. Wooldridge 10.1-10.7. |

CT=Cameron&Trivedi, Am=Amemiya, DM=Davidson&MacKinnon,
Gr=Greene, Mad=Maddala,

W = Wooldridge.

**Required Material:**

Cameron, A.C. and P.K. Trivedi (2005), Microeconometrics: Methods and Applications, Cambridge University Press.

Much of the class will follow this book. The book is at times more detailed than what will be covered in this class.

**Recommended Material:**

These are more than you can buy but are good to have in a
microeconometrics library. I have not ordered these for the
bookstore, but still recommend their purchase - in the sequence
close
to what I would consider buying them in. You should already have
Greene. These books can be ordered on-line.

Greene, W.G. (2007), *Econometric Analysis*, 6th edition,
Prentice-Hall.

Wooldridge, J.M. (2010), *Econometric Analysis of Cross
Section
an Panel Data*, 2nd edition, MIT Press.

Maddala, G.S. (1983), *Limited-Dependent and Qualitative
Variables in Economics*, Cambridge University Press.

Amemiya, T. (1985), *Advanced Econometrics*, Harvard
University Press.

Davidson, R. and J.G. MacKinnon (2004), *Econometric Theory
and
Methods*, Oxford University Press.

Cameron, A.C. and P.K. Trivedi (1998), *Regression Analysis of
Count Data.
*

Cameron, A.C. and P.K. Trivedi (2009, revised ed. 2010), Microeconometrics using Stata, Stata Press.

Greene (which you should have from 240A,B) is useful for more
elementary treatment of topics.

Wooldridge is at similar level to Cameron and
Trivedi with more on linear models and not as much on nonlinear
models
and related topics. It is also more formal econometrically.

The second edition is a significant expansion on the first
edition,
especially Nonlinear Models and Related Topics.

Maddala is the standard reference for introductory
treatment of probit, logit and probit models and is cheap in
paperback.

Amemiya was the standard book before D&M (1993) and even now
has an
excellent advanced treatment of limited dependent and discrete
choice
models.

D&M is an updated and somewhat less advanced version of
Davidson,
R. and J.G. MacKinnon (1993), *Estimation and Inference in
Econometrics*, Oxford University Press. It emphasises
econometric
theory.

Cameron and Trivedi (1998) focuses on count data models, but
includes
many general results and approaches for nonlinear regression,
especially in chapters 3 and 5, and is cheap in paperback.

Cameron and Trivedi (2009, 2010) focuses on use of Stata and
covers
most
microeconoemtrics models.

These recommended books emphasize cross-section data. For panel
data,
which we have little time for in this course, Cameron &
Trivedi and
Wooldridge provide considerable coverage.

In addition
econometrics panel data books are:

Baltagi, B.H (2001), *Econometrics Analysis of Panel Data*,
2nd
edition, Wiley.

Hsiao, C. (2003), *Analysis of Panel Data*, 2nd edition,
Cambridge University Press.

Lee, M.J. (2010), *Microeconometrics: Methods of Moments and
Limited Dependent Variables*, 2nd edition, Springer.

Arellano M. (2003), *Panel Data Econometrics*, Oxford
University
Press.

**Additional Materials:**

Selected papers can generally be downloaded from the web, mostly using JStor.

**Computer Materials:**

**Stata: **Assignments will use STATA. STATA is available on
both Econ
and ARE computers.

More complicated models require use of a matrix programming
language.
We will use the new MATA inrtroduced in Stata 9, rather than GAUSS
or
MATLAB.

Most course material is at smartsite.ucdavis.edu (some is
at
cameron.econ.ucdavis.edu/e240d/e240d.html )

Some further computer information will be available at my personal
home page: cameron.econ.ucdavis.edu

Assignments 15%

Best 5 out of 6. Last assignment is compulsory. Each worth 3%.

Due **Thursdays Jan 19, 26; Feb 2, 23; March 8, 15**.

Midterm 35%

Thurs**day Feb 9 in
class**

Final 50%

Satur**day March 24
3.30 – 5.30 p.m. Comprehensive**.

No credit for late assignments. Lowest assignment score is dropped.

Academic integrity is required. What is academic integrity? See the UCD Student Judicial Affairs website http://sja.ucdavis.edu/integ.htm.

As an exception to their rules, I permit some collaboration with other students in doing assignments, but the work handed in must be your own. Each person must create their own Stata output and write up their own answers. And you are to write on your assignment the name of the person(s) you worked with.

Exams will be closed book. The final exam is comprehensive.