This course covers some of the most important methodological issues arising in any field of applied economics when the main scope of the analysis is to estimate causal effects. A variety of methods will be illustrated using theory and papers drawn from the recent applied literature. The aim is to bridge the step from a technical econometrics course to doing applied research. The emphasis will be on the applications. The goal is to provide students with enough knowledge to understand when these techniques are useful and how to implement each method in their empirical research.

Part 1 (C. Tealdi):
- The simple regression model
- Estimation
- Inference
- Dummy variables
- OLS Asymptotics
- Heteroskedasticity
- Instrumental Variables

Part 2 (A. Belmonte):
- A quick introduction to STATA
- Microeconomic data structures
- Conditional distributions and the conditional expected function concept
- A discussion of the assumptions of the GM Theorem
- Heterogeneous conditional distributions
- Dummy variables and Anova models
- Autocorrelation and the Moulton factor

Part 3 (P. Zacchia):
- Beyond Single-Equation Linear Models: Structural Models, Identification and Causality; Rubin Causal Model
- Simultaneous Equation Models
- Introduction to M-Estimation
- Generalized Method of Moments
- Maximum Likelihood Estimation
- Non-Parametric Estimation

Part 4 (A. Rungi):
- Benefits and limits of panel data structures; Review of some panel data examples for micro- and macro data; How to handle and describe panel data; basic estimation techniques
- Details for panel data estimators
- Identification problems
- Introduction to non-linear panel data estimators
- Count data models

Prerequisites: Linear Algebra + Found. of Prob. & Stat. Inf.