EC 671

 

Advanced Econometrics

EC671

 Professor Junsoo Lee

Syllabus

[NOTE: This site will not be updated.  Instead, DROPBOX will be used.]

 

DATA SETS and CODES for textbook examples

Wooldridge Data sets via Baum | Sources of the data sets | Datasets from the STATA site

STATA procedures (Wooldridge) | RATS procedures for Wooldridge data sets

 

Verbeek site

 

Greene's Official Site (data sets, limdep examples..)  | Greene Data sets via Baum

 

DATA / PANEL DATA

RFE (Resources for Economists) DATA LINKS

 PSID (Panel study of income dynamics)

  NLS (National Longitudinal Survey of Youth 1997 (NLSY97)

 Start here  author list title list source list;     keyword search

 

STATA RESOURCES

Use of STATA in Textbooks

Stata class notes with movie! (UCLA)

J & J Note

Resources for learning STATA

 

Econometrics Handbook  (Volume 1 - 4 free pdf files, 5 - 6)

Three tests (undergraduate/MA econometrics): Exam 1, Exam 2, Exam 3

Greene textbook, Typos  | His book link

 

STATA Help

Help

 

OUTLINE

[Revised Lecture Notes, 2010]

Lecture 1 (Revised, 2010) Panel I (also, see below; previously Lecture 5 or Note 5)

Lecture 2 (Revised, 2010) Panel II (also, see below; previously Lecture 6 or Note 6)

Corrections on Lectures 1 and 2

IV Estimation (Added Lecture)

Lecture 3  (Revised, 2010) M-Estimation 

Lecture 4 (Revised 2010) MLE (also, see below; previously Lecture 7/8 or Note 7/8)

Lecture 5 (Revised, 2010) Binary Discrete Choice Models (also, see below; previously Lecture 9 or Note 9)

 

******************* SUMMARY ********************

-------------------  Review of EC 670 -------------------------------------------

Old Note 1 Review of Regression Analysis and Extension  | Older Note 1 

Old Note 2 Review of Instrumental Variables Estimation |  Older Note 2 

Old Note 3 Review of Additional Single-Equation Topics | Older Note 3 

Old Note 4 Review of  System of Equations Models | Older Note 4  

-----------------  Main Topics in EC 671 ---------------------------------------

Old_NOTE5    Old 2007 Note 5�� Panel Data Models (I)    | Older Note 5 

Old  Old 2007 Note 6  Further Topics in Panel Data Models (II)  | Older Note 6   

Old  Old 2007 Note 7  Note 7: Maximum Likelihood Estimation Older Part I, Part II, and Part III

Old  Old 2007 Note 8  M-estimator, GMM, and Minimum Distance Estimation | OLD Note 8 

Old  Old 2007 Note 9  Binary Discrete Choice Models | Older Note 9 

Added I (delta method)  | Added II (interaction)

Old   Old 2007 Note 10  Extended Choice Models | Older Note 10 

Old   Old 2007 Note 11  Corner Solution Outcomes and Censored Regression Models | Older Note 11  

Note 12  Selection Bias Models and Average Treatment Effects Models | OLDer Note 12 

Note 13   Count Data Models | Older Note 13  

Note 14  Stochastic Frontier Models | Older Note 14  

Note 15  Duration Models | Older Note 15 

Note 16 Non-linear Panel Data Models (III) | Older Note 16  

 

========================================

Part I.  Review of Linear Regression Models *

            (* will go fast)

1.  Regression Analysis and Extension

Read: CT 1.6, 4, 7; Wooldridge Ch 4; Verbeek Ch 2, Ch 3, 4.10; Green Ch 2, 3, 4, 6

NEW Note 1  | old Note 1  Word file (not proofread)

Problem Set 1

Problem Set 2

Self test 1

STATA example and h/w data  asset2.do (code)    asset_pricing.zip (data files)   fashion_stores.zip (clothing data)

10 Papers that Dr. Cook recommends for finance doctoral students.

Linear Algebra of OLS Estimation

(common ground)

              Assumptions in OLS and Asymptotic Inference Using OLS

              Heteroskedasticity-robust Inference

       HAC Standard errors

                GLS and WLS (CT 4.5)

       Testing Hypothesis and 3 Tests

       Sources of the Endogeneity Problem

              Treating Unobservables

              Nonlinear Models

       Testing for Structural Breaks

       Use of STATA and Empirical Exercises

 

2.  Instrumental Variables Estimation

Read: CT 2.4, 4.8-4.9; Wooldridge Ch 5, 9; Verbeek Ch 5; Green Ch 5

 NEW Note 2 | old Note 2 (pdf)    Word file (not proofread)

  Read: Levitt's paper

  2SLS stata examples | data | excel | 2sls example (word file) | 2sls.do

Problem Set 3

               Instrumental Variables Estimation and 2SLS

               Testing for Endogeneity

  • Endogeneity test and 2SLS: Mroz data

               Potential Pitfalls with 2SLS

               Issues regarding Weak Instruments

** Murphy_Topell correction | Summary (revised) | STATA code | data(mroz.dta) | output | Jing's comment | limdep code

               OLS with Generated Regressors and IVs

               GIV, GMM estimator (Wooldridge Ch 13, 14)

                GMM in Limdep examples | mroz.dat | mroz.des (description)  

                Verbeek zip file including the example for Consumption based Asset Pricing Model: RATS example (verbeek154.prg)

o    Eviews example

       GMM Example Papers in Finance

                  Huang and Stoll (RFS, 1997)

                  Hennessy (JF, 2004)

                  GMM and C-CAPM (2003, WP)

 3.  Additional Single-Equation Topics

NEW Note 3 |  Old  Note 3 (pdf)   Word file (not proofread)

Read: CT 4.6; Wooldridge Ch 6; Green Ch 7

References:

Read: Heckmit's standard errorMurphy and Topel, and Alternative

Read: D-i-D estimator and Trade liberalization | Meyer et al AER 1995

Read: How much do we trust d-i-d?

 

       Other sampling schemes

 

Quantile regression (Koenker)

 

4. System of Equations Models (Moved from Part I)

 NEW Note 4 | Old Note 4

Read; CT 6.9-6.10; Wooldridge Ch 7; Green Ch 14

Problem Set 4

               Seemingly Unrelated Regressions

               GLS

               Endogeneity and GMM in system of equations

 

4.  Specification Tests and Model Selection

Read CT 8

 

=================================

Part II.  Linear Unobserved Effects Panel Data Models

 1.  Panel Data Models (I)

        *** Lecture 1 (Revised, 2010) Panel I ***

Old_Note5    Old 2007 Note 5  | older Note 5

Stata Examples: wagepan.do (code)   wagepan.dta (data)

Manual

 

hw 1 | hw 2

         PSID (Panel study of income dynamics)

         NLS (National Longitudinal Survey of Youth 1997 (NLSY97)

o    Start here

o    title list

o    source list

o    keyword search

Panel data models: example, crime in Brazil

Wooldridge Ch 10; Verbeek Ch 10.1-10.3; Green Ch 13 

              Advantages of Panel data models and Unobserved heterogeneity

       Three Approaches

o      First Difference (FD)

o      Fixed Effect (FE) Models

o      Random Effect (RE) Models

              Choosing between OLS, FD, FE, BE or RE models

 

Someone's excellent notes on Panel data models (easy but good discussions and good examples)

 Notes: 1, 2, 3, 4, 5 | 6 (dynamic) | 7 (choice, FE), 8 (choice RE) | 9 (GEE) | 10 (count)

 

2.  Further Topics in Panel Data Models (II)

     Lecture 2 (Revised, 2010) Panel II 

  Old Note 6   |  older Note 6

Wooldridge Ch 11; Verbeek Ch 10.4-10.8; Green Ch 13

       Hausman and Taylor method

       Dynamic Linear Models

       Cluster Samples

       Recent Issues in Panel data models

Manuals Backup copy: Read  (1) abond and (2) dpd (new)

Stata files:

                Panel IV estimation (xtivreg.do | xtrivreg.log )

                Hausman & Taylor Method (Stata do file | data set | log file )

                Dynamic panel

o    TSP archives for Dynamic Panel Data models

o    STATA example (stata example | data)

References:

                Lemieux paper | Hoxby paper | Friedberg paper | Levine's Bad smoking paper

Fama and MacBeth :

                Original Paper

                Example 1 | Example 2 | Example 3 | Example 4 | Example 5 (Fama French) | Example 6 (Fama French) |

IV Estimation (Added Lecture) 

Part III.  Review of General Estimation Methods *

      Wooldridge Ch 12, 13, 14; Verbeek Ch 6; Green Ch 17, 18

           (* will go fast)

Lecture 3  (Revised, 2010) M-Estimation 

        GMM examples Stata codes| Output (email) 

Lecture 4 (Revised 2010) MLE

(a)  Maximum Likeihood Estimation

   NEW Note 7�� |Old Note 7: Part I, Part II, and Part III

              Properties of MLE

              Hypothesis Testing

              Preliminary and Examples

                Examples 

o    Ex1 (Linear)

o    Ex2(Gamma)

o    Ex3 (weibull data)

o    Ex4 (logit)

o    Ex5 (probit)

o    Ex6 (Poisson) | another

o    Ex7 (Linear using own gradient)

o    Ex8 (Poisson using own gradient)

o    Ex9 (tobit)

o    Ex10 (ordered probit)

o    Ex11 (negative binomial)

o    Ex12 (duration)

Exercises

                Exercise homework

 Problem Set 5

 

(b)  M-estimator, GMM, and Minimum Distance Estimation

NEW Note 8 | Old Note 8 

M-estimator, Extreme estimator and Properties of GMM

      IVGMM stata note

 

Part IV.  Advanced Cross-Sectional Econometric Models

 

1.  Binary Discrete Choice Models

Wooldridge Ch 15; Verbeek 7.1; Green 21.2-21.5

  Old Note 9  | Older Note 9

 Added I (delta method)  | Added II (interaction)

       Review on Probit and Logit Models

       Latent Index model? Advantages of LPM?

       Issues for these models

                Endogeneity issue

                Choice based sampling

                On heteroskedasticity and non-normality

                QMLE and sandwich estimator

       Panel Choice Models

              Examples and Review

                    (old) choice_binary (output | stata code)

                    (revised) choice_binary (stata code file: choice_binary-revised.do  | output | )

                    AACSB example (question and stata | excel file data)

                     WLS example (Greene Ch 12; copied)

                    Panel RE/FE probit and logit models (stata code xtprobit_logit.do | output | smcl output file)

** Murphy_Topell correction | Summary (revised) | STATA code | data(mroz.dta) | output | Jing's comment | limdep code

         Read:   Sandwich estimator for the variance in logit or probit, Why?

 

2.     Extended Choice Models

Old Note 10  | Older Note 10

      Wooldridge Ch 15; Verbeek 7.2; Green 21.7-21.8

         Multinomial Logit and Conditional Logit Models

       IIA assumption

       Nested Logit Models

       Ordered Probit Models

       Panel Models

              Examples and Review

Example of extended choice models

     stata code extended_choice.do | output word file |

Try this (logit-low1.do).  So, "clogit, group(pair)" and "paired logit" produced the same results. Jing wrote a user-defined code for this issue.

Exercise questions

Data file:  TBL19-2.dta

 

3.     Corner Solution Outcomes and Censored Regression Models

   Old Note 11  | Older Note 11

Wooldridge Ch 16; Verbeek 7.4-7.5; Green 22.1-22.3

              Inconsistency of OLS

              Estimation and Inference with Censored Tobit

              Censoring and Truncated Regression Models

       Panel Models

              Examples and Review

                 Stata code tobit_cnreg_intreg.do | output log file | word file output

 

4.     Selection Bias Models and Average Treatment Effects Models

Note 12

Wooldridge Ch 17, 18; Verbeek 7.6; Green 22.3-22.4

             Censoring, Truncation and Incidental Truncation

            Two Stage estimation of the Tobit Model

            Models with Self-selectivity

            Corrected Standard Errors of Generated Regressors

       Other extended models

       Panel Models

              Counterfactual Setting and the Self-Selection Problem

              Propensity Score Matching Methods

              Differences-in-Differences Method

       IV Estimation

 

              Examples and Review

                Stata code heckman_selection.do | output log file | word file output

                PSM example: 

  This needs two files: psmatch.do | psmatch.ado | pamatch.hlp | pdf document for this

 

5.     Count Data Models

Note 13

Wooldridge Ch 19; Verbeek 7.3; Green 21.9

       Count Data

       Poisson regression models

              Negative binomial models

       Hurdle, ZIP and ZAP Models

              Endogeneity Issue

       Panel Count data models

              Examples

                Stata code and output files :  poisson_negbin.do | output log file | word file output

                Limdep code and outputs   :  POISSON.LIM | poisson.out | poisson.lpj 

                Limdep code and outputs   :  count_hw.lim | crime1.dat | fertil1.dat

 

6.     Stochastic Frontier Models

 Note 14

(Reference Papers, Green p. 429, 501-505)

       Various Frontier Models

              Efficiency Measures

       Ranking airline companies or banks? 

       Why can�t we use residuals? 

              Technical efficiency, allocation efficiency

              Stochastic Frontier Models

       Panel Data Stochastic Frontier Models

              Examples and Review

                Stata code and output files :  frontier.do | output log file | word file output | frontier.txt

 

7.     Duration Models

Note 15

Wooldridge Ch 20; Verbeek 7.8; Geeen 22.5

               Duration and Transition Data

       Hazard and survival functions

              Non-parametric Approach

       Plot of Hazard Rates

              Homogeneity test

              Semiparametric and Parametric Duration models

              Proportional Hazard Models

              Parametric Duration Models

              Examples and Review

STATA example:

duration2.do   duration2.doc  duration2.log

duration.do   duration.txt  duration.doc  duration.log

LIMDEP example:

DURATION2.LIM  duration2.out 

duration.lim  duration.lpj  duration.out 

duration_hw.lim  

8.     Panel Data Models (III)

Note 16

(Total Review of ) Panel Data Models for Limited Dependent variables Models

Integrating-out and Conditioning-out methods

GEE models

Latent Class models

Survey paper by Greene (good! Read this!)

Panel RE models Review in STATA (good! Skim through this!)

Recent developments in Panel data models (survey by Arrelano and Bonore)

 

Bootstrap Examples

    Jing's note (basic bootstrap in stata) | example code bootstrap.do

    Gauss codes: boot_block.g |   boot_s_mean_ci.g  |  ec671/boot_reg_res.g