• Votre sélection est vide.

    Enregistrez les diplômes, parcours ou enseignements de votre choix.

Public policies assessment in econometrics (DROI852_SOLEM )

  • ECTS

    1 crédits

  • Composante

    Polytech Annecy-Chambéry

Description

  • Semester 8
  • Duration :  Within one semester  
  • Type: Mandatory
  • Student workload:  Lecture (CM): 10,5 hours 

  • Applicability: SOLEM course only 

  • Module examination:  1 written exam (50%), 1 individual oral presentation (30%), Readings (20%)
  • Teaching and learning method : seminar, case studies,  discussion.

 

Responsible person for the module: Adan L. Martinez-Cruz, Associate Professor, Department of Forest Economics, Swedish University of Agricultural Science (SLU) 

Lire plus

Objectifs

By the end of the course, students will be able to:

  • explain the conditions under which an impact evaluation exercise can be carried out; 
  • verify that such conditions hold in a specific context; and 
  • implement an impact evaluation exercise. 
Lire plus

Heures d'enseignement

  • Public policies assessment in econometrics - CMCours Magistral10,5h

Pré-requis obligatoires

Admission to 2nd semester

Lire plus

Plan du cours

 

Date (time) 

Topics 

Material/Activities 

April

  1. What is an impact? 
  1. What is an evaluation? 
  1. What is an experiment? 
  1. Why and when do we want to carry out an impact evaluation exercise? 
  1. How can we carried out an impact evaluation in a non-experimental context? 

Netflix Research: Experimentation and causal inference. 

 

Ideal experiment. 

 

Quantifying causality with quasi-experiments 

 

Ten reasons not to measure impact –and what to do instead. 

 

Optional, strongly recommended: 

Introduction to Causal Inference: Philosophy, Framework and Key Methods PART ONE 

 

May 

  1. Impact evaluation in non-experimental context. 
  1. Quasi- (pseudo-) experiments 
  1. Seeking for statistical twins a posteriori (Propensity matching score) 
  1. Seeking for statistical twins a priori (Difference-in-difference) 
  1. Generating ideal statistical twins (Machine learning)  
  1. What about when outcome variable is not linear? 

Impact Evaluation in Practice, Second Edition. 

 

The effect of alcohol availability on marijuana use: Evidence from the minimum legal drinking age. 

 

Poverty and Witch Killing. 

 

Machine Learning and Causal Inference for Policy Evaluation. 

The impact of emissions-based taxes on the retirement of used and inefficient vehicles: The case of Switzerland. 

 

Optional, strongly recommended: 

Introduction to Causal Inference: Philosophy, Framework and Key Methods PART TWO 

How Much Energy Do Building Energy Codes Save? Evidence from California Houses 

May

 

 

 

Student’s presentation 

 

* Remote class 

** On-campus class 

Lire plus