Statistical Methods and Applications

ANDREA MERCATANTI

Learning goals
The primary learning goal of this course is that of exposing students to the body of econometric techniques that are customised to economics applications. The aim of the course is to review this body of techniques, to demonstrate their use in hands-on style, drawing on as wide a range of example as possible, and to interpret each set of results in ways that are most useful to read and represent economic phenomena.

Knowledge and understanding.
The course is supposed to broaden students' knowledge of the various econometric techniques that appear in the economics literature, their properties and the way these are applied to data in order to verify economic theory.

Applying knowledge and understanding.
Upon successful completion of the course, students will be able to carry out a wide range of tasks in empirical economics, such as recognising the most suitable approaches to analyse the data at hand in order to capture and model its regularities, and intelligibly convey its messages to both economists and broader audiences.

Making judgements.
The course develops in a way to spurs students on researching empirical evidence of competing economic theories by respecting the nature of convenient data.

Communication skills.
Through study and hands-on sessions, students will acquire the terminology characterising the discipline, which they are required to use in both written and oral dissemination.

Learning skills.
Students who complete the course successfully will be acquainted with a method of analysis enabling them to endeavour the main economic issues from an empirical point of view.

Learning goals.
The aim of the course is to introduce students to the main methods for the identification and estimation of causal effects in micro-econometrics and policy evaluation. In particular, it covers
i) methods under ignorability (exogeneity) of the treatment assignment: regressions, methods based on propensity score, matching.
ii) methods under non-ignorability (endogeneity) of the treatment assignment: Instrumental Variables (Local Average Treatment Effect), Regression Discontinuity Designs, Difference-in-Differences and Synthetic Control Method.
Knowledge of the econometric theory for cross-section analysis, inference and probability theory is a prerequisite.

Knowledge and understanding.
After attending the course the students know and understand the main problems related to causal inference in econometrics (for example: the endogeneity of the treatment assignement) and the main methods to be used to solve such problems (for example: the use of the propensity score and the latent factor structure of causal models).

Applying knowledge and understanding.
At the end of the course the students are able to formalize real problems in terms of econometric causal models and to apply the methods specific to the discipline to solve them.
They are also able to apply the methods to concrete situations and to interpret the results.

Making judgements.
Students develop a knowledge of the analytical properties of the presented methodologies and the ability to build programs for their implementation.
They also learn to critically interpret the results obtained by applying the procedures to concrete situations.

Communication skills.
Students acquire the technical-scientific language of the discipline, which it must be used appropriately in the final written tests and in the oral tests.
Communication skills are also developed through group activities.

Learning skills.
Students who pass the exam have learned a set of econometrics methods appropriated to conduct high-quality empirical research in causal econometrics and policy evaluation

APPLIED ECONOMETRICS program:

Introduction to the potential outcome approach.
Neyman's mode of inference.
Outcome regression.
Propensity score.
Propensity score weighting.
Doubly robust estimation.
Instrumental variables.
Causal methods for panel data: difference-in-differences.
Regression discontinuity designs.

- Angrist, J. D. & Pischke, J.-S.: Mostly Harmless Econometrics: An Empiricist’s Companion (Princeton Univ. Press, last edition).
- P. Ding: A First Course in Causal Inference (Chapman & Hall/CRC Texts in Statistical Science) 1st Edition, 2024.

A written exam is planned to assess both the acquisition of theoretical concepts and the ability to solve practical problems.