93304 - VALUTAZIONE POLITICHE PUBBLICHE

Learning outcomes

The course aims to develop foundational knowledge and skills related to the methodological framework and tools for evaluating the effects of a policy or intervention. By the end of the course, students will be able to: a) understand the methodological framework and basic statistical techniques for policy evaluation; b) identify the most appropriate technique based on the available data; c) apply some techniques to estimate effects and interpret the results.

Course contents

Prerequisites

To successfully follow the course, students are expected to have basic knowledge of statistical inference (estimation and hypothesis testing) and linear regression (as covered in the second-year Statistics and Data Analysis course).

Course Content

Introduction to Policy Evaluation:

• Definition and goals of evaluation
• Implementation evaluation vs. impact evaluation
• Distinction between evaluation and monitoring

Impact Evaluation and the Counterfactual Approach:

• Designing an impact evaluation: outcome variable and treatment variable
• Counterfactual approach and the potential outcomes model; definition of impact
• Threats to the validity of impact evaluation: selection bias and spontaneous dynamics (omitted variables bias)
• Estimation strategies: control group designs, experimental and quasi-experimental designs
• Experimental design (overview)

Impact Evaluation with Quasi-Experimental Designs:

• Difference-in-Differences (DID): when it can be applied, assumptions and estimation, limitations
• Use of regression to implement DID
• Regression Discontinuity Designs: when it can be applied, assumptions and estimation, limitations
• Propensity Score Matching: propensity score and matching methods, data, assumptions and estimation, limitations

Applications

• Application of methods to case studies involving labor market, welfare, and business policies.

Readings/Bibliography

The course will be mainly based on lecture notes and papers provided through the e-learning platform Virtuale

Recommended Reference Books:

• Martini, A. and Sisti, M. (2009). Valutare il successo delle politiche pubbliche. Il Mulino. Chapters I, VI, VII, VIII (only sections 1, 2, and 4), IX, X (sections 1 and 4; section 5 for consultation), XI, XII.
• Stock, J.H. and Watson, M.W. (2016). Introduction to Econometrics, 4th Edition, Pearson (Italian edition edited by Franco Peracchi). Sections 1.2, 3.4, 3.5, 5.3, and Chapter 13 (up to section 13.5).

For a review of concepts in statistical inference and regression, the following may be consulted:

• Borra, S., Di Ciaccio, A. (2021). Statistica, metodologie per le scienze economiche e sociali, McGraw-Hill, 4th Edition (Textbook for the course Statistics and Data Analysis).
• Stock, J.H. and Watson, M.W. (2016). Introduction to Econometrics, 4th Edition, Pearson (Italian edition edited by Franco Peracchi). Chapters 3, 4, and 5.

Teaching methods

The course is structured into lectures, which cover theoretical aspects illustrated through examples, and practical activities conducted in class.

The practical activities involve the use of statistical software (Stata) to apply the methods presented during the theoretical lectures to real data.

The software can be downloaded and installed free of charge by each student on their own computer. To actively participate in the practical sessions, students are required to bring their own laptop to class.
Students who do not have access to a personal laptop can still participate by working in pairs with a classmate.

Assessment methods

The exam consists of a written test lasting 75 minutes, to be taken in person at the end of the course, and will be the same for both attending and non-attending students.

The written test will include questions covering both theoretical and empirical aspects discussed during the course and will be divided into two parts:

1. A section with multiple-choice or short open-ended questions on all topics covered in the course (8–10 questions).

2. A section presenting the output of the statistical software used to analyze a case study discussed during the course. The student must answer four questions, which may involve interpreting the results or addressing other aspects of the analysis shown in the output.

The two parts will have equal weight in the final evaluation (maximum of 16 points each).

The written test is designed to assess:

• knowledge of concepts and techniques for impact evaluation;
• the ability to structure and interpret the evaluation design (choice of outcome variables, treatment variable, and method based on data);
• the ability to interpret estimation results;
• clarity and completeness of the answers
• the ability to use formal language appropriately.

The grading scale will be as follows:

• <18: insufficient
• 18–23: sufficient
• 24–27: good
• 28–30: very good
• 30 with honors: excellent

Further information will be provided during the course.

Teaching tools

1) The VIRTUALE platform [https://virtuale.unibo.it/] , will provide students with:

• Lecture slides and notes
• Dataset and code for lab sessions
• Additional readings material (articles, etc.)

Materials will be provided and updated throughout the course.

2) For the in-class practical sessions, it is necessary to install the STATA software (SE version) on your personal computer. UNIBO has activated a Campus license, which allows all UNIBO students to download and install the software. You can download the software using the following link: https://www.unibo.it/secure/software-stata/. Please also download the accompanying documentation with instructions for license activation.

Office hours

See the website of Pinuccia Pasqualina Calia