Logo Doctoral Certificate Program in Agricultural Economics
Course of Study

Module 6500
Advanced Applied Econometrics 2:
Limited Dependent Variable (LDV) / Choice models


Prof. Dr. Thomas Heckelei,  thomas.heckelei@ilr.uni-bonn.de
Prof. Dr. Stefan Hirsch, stefan.hirsch@tum.de


At the end of the course students shall

Skills: Methodological competence, quantitative analysis, conceptual thinking



  1. Maximum Likelihood Estimation (Verbeek Ch. 6.1 and 6.2
    • Introduction to and examples for ML estimation
    • General approach and estimation of the variance of the ML estimator
    • Specification Tests
  2. Binary Choice Models (Verbeek Ch. 7.1)
    • Why not Linear Regression?
    • Probit and Logit models
    • Underlying latent variable model
    • Estimation
    • Goodness-of-fit
    • Specification tests
  3. Multiple Choice Models
    1. Ordered Response Models (Verbeek Ch. 7.2, Greene Ch. 18.3)
      • Introduction
      • The ordered probit model
      • Estimation, Effects and Interpretation
      • Testing
    2. Multinomial Models (Verbeek Ch. 7.2, Greene Ch. 18.1-18.2)
      • Introduction, formalization, distributions
      • The conditional logit model: introduction, estimation and interpretation
      • The multinomial logit model: introduction, estimation and interpretation
      • Independence of irrelevant alternatives IIA assumption
      • The nested logit model: : introduction, estimation and interpretation
  4. Count data models (Verbeek Ch. 7.3)
    • General motivation
    • Poisson model
    • Negative Binomial Model
    • Illustrations
  5. Tobit models (Verbeek Ch. 7.4-7.5)
    1. Tobit I
      • Utility maximisation problem
      • Standard Tobit model
      • Tobit estimation
      • Tobit specification test
    2. Tobit II (Double Hurdle)
      • Statistical model
      • Heckmann selection model
      • Estimation
Teaching forms Workload (h)
1 week block seminar with lecture and exercise 40
Exercises 50
Total 90

Examination: Exercises

Grading: In-class and homework assignments, where a minimum score of 50% is required to pass the module.

Credit points: 3 CP

Requirements: Basics in econometric course or
module 2500 AAE-1: Linear Models and Panel Data or
module 7600 Applied Microeconometrics and Impact Analysis

Language: English


Software: R

During the course all exercises can be conducted in R or Stata, while support will be given in R only and our handouts will be in R. If R is new to you please familiarize yourself with basics in R.