Andreas Beerli: Catalogue data in Spring Semester 2023 |
| Name | Dr. Andreas Beerli |
| Address | KOF FB KOF Lab ETH Zürich, LEE G 116 Leonhardstrasse 21 8092 Zürich SWITZERLAND |
| Telephone | +41 44 633 82 35 |
| beerli@kof.ethz.ch | |
| Department | Management, Technology, and Economics |
| Relationship | Lecturer |
| Number | Title | ECTS | Hours | Lecturers | ||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 363-0570-00L | Principles of Econometrics Prerequisites: previous knowledge in economics. | 3 credits | 2G | J.‑E. Sturm, A. Beerli | ||||||||||||||||||||||||||||||||||||||||||||
| Abstract | This course introduces the fundamentals of econometrics. We cover simple and multiple regression analysis using different data formats. An emphasis is on hypothesis testing, interpretation of regression results, and understanding threats to the causal interpretation of relationships in the data. | |||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The course targets both the theoretical understanding as well as the application of basic econometric methods to real world problems. The educational objective of this course is that, after completion, students should be able to: 1. understand different forms of data (cross-sectional, panel, time-series) and their strengths and weaknesses for answering different research questions. 2. understand how to translate questions about economic policy issues and human behaviour into research hypotheses that can be tested with data. 3. apply their theoretical knowledge about econometrics to concrete examples based on the knowledge they acquired in tutorial sessions using the statistical software package STATA and interpret estimation results. 4. name and identify potential threats for causal interpretations of relationships in the data and explain whether (and how) they can be addressed. | |||||||||||||||||||||||||||||||||||||||||||||||
| Content | The term “econometrics” stands for the application of specific statistical methods to the field of economics. Econometrics aims at providing empirical evidence using observational data that can be used to learn about the real-world existence of specific relationships postulated in economic theories. Typical research questions that economists analyse by using econometric methods include for instance: Do minimum wages reduce employment? Does a gender wage gap exist and how large is it? Does foreign aid affect economic growth? How do interest rate changes influence exports? Is there an effect of economic outcomes on politicians’ chances to get re-elected? Starting from simple regression analysis, the course introduces the statistical framework that is used in econometrics to answer such empirical research questions. A major focus is on understanding and mastering methods of hypothesis testing using multiple regressions. The lecture discusses different issues regarding assumptions, interpretation, and inference in multiple linear regression models. Among others, the course addresses the following questions: How well or badly does the applied model fit the observed facts? How large is the estimate of the effects of one variable on another and how reliable is the estimate? Can the model be used to predict the specific variable of interest and how precise is that prediction? What are the crucial assumptions of the estimation strategy used, (how) can they be tested, and does the estimated relationship represent a causal effect? The course lectures introduce the methods and computer tutorials give the students the opportunity to apply and deepen their knowledge using the software package STATA. | |||||||||||||||||||||||||||||||||||||||||||||||
| Literature | Wooldridge, Jeffrey M. (2018) Introductory Econometrics : A Modern Approach. Seventh ed. ISBN: 978-1-337-55886-0 [access to relevant chapters will be provided] | |||||||||||||||||||||||||||||||||||||||||||||||
| Prerequisites / Notice | This course is intended for students interested in econometrics who have already taken an introductory course in economics (e.g., the course "Principles of Macroeconomics"). Knowledge of the statistical software STATA is no prerequisite and will be acquired during the course. | |||||||||||||||||||||||||||||||||||||||||||||||
Competencies |
| |||||||||||||||||||||||||||||||||||||||||||||||
| 364-1169-00L | Evaluating Social Impact with Field Experiments | 3 credits | 2G | A. Beerli | ||||||||||||||||||||||||||||||||||||||||||||
| Abstract | How can we evaluate whether a new policy, program, or service changes individuals’ behavior and makes a difference in their lives? How can we measure its social, economic, etc. impact? This course introduces the fundamentals of field experimental methods for social scientists. We will cover all important ingredients to design, conduct, and learn from randomized controlled field experiments. | |||||||||||||||||||||||||||||||||||||||||||||||
| Learning objective | The main objective of the course is to empower students to run their own experiments in the field. After the course students will 1. be able to identify opportunities to run experiments, assess their feasibility, and learn which questions need to be sorted out with field partners right at the beginning 2. understand different experimental designs and their strengths and weaknesses 3. understand the ethical challenges inherent to field experiments and whether and how they can be addressed 4. know how to combine register data and surveys to measure outcomes 5. know how to prevent or handle key implementation issues, such as non-compliance, spillovers between treatment and control group, attrition or non-response | |||||||||||||||||||||||||||||||||||||||||||||||
| Content | This course is designed for PhD students in social sciences (such as economics, political science, psychology, etc.) or other fields working with human subjects who would like to run their own experiments in the field. A background in basic econometrics and probability theory is required, knowledge in causal inference is helpful. In contrast to working with observational data and quasi-experimental methods, running field experiments allows researchers to have larger control over the data generating process. This requires, however, to think about ways to address the most important challenges before the experiment is conducted. Knowing these key aspects of designing field experiments, measuring outcomes and collecting data, and potential implementation issues that could arise, will allow students to assess quickly whether an experiment is feasible or not and how challenges to the validity of the experiment can be addressed in collaboration with field partners. In the course we will cover all important aspects to successfully design and conduct randomized controlled experiments (or randomized controlled trials, RCTs) in the field. The first part of the course focuses on the set up of field experiments: different designs and sample size, ethics considerations, transparency and open science best practices, survey design and organizing data collection. The second part covers implementation issues: one-sided and two-sided non-compliance, attrition or non-response, and spillovers between treatment and control group. The course grade is based on a written research proposal of an original idea for a field experiment. | |||||||||||||||||||||||||||||||||||||||||||||||
| Competencies |
| |||||||||||||||||||||||||||||||||||||||||||||||