Inglese

- Richiami delle distribuzioni di probabilità

- Test di ipotesi e inferenza

- Regressione lineare

- Esperimenti randomizzati classici

- Progettazione di meccanismi di assegnazione regolare

"Applied Statistics and Probability for Engineers" by Douglas Montgomery and George Runger.(Ch. 9-13)

"Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction" by Guido W. Imbens and Donald B. Rubin. (Part I, II and III)

Questo corso introduce i principi del disegno della ricerca sperimentale con particolare attenzione all'inferenza causale. Impareremo a valutare se dei trattamenti hanno un effetto sulle unità sperimentali (es. trials clinici). Si esplorano dapprima i test di ipotesi paired e l'analisi di regressione, per poi trattare in dettaglio la teoria dell'inferenza statistica negli esperimenti randomizzati. Si considera anche l'inferenza causale per gli studi osservazionali. Il corso è progettato per fornire agli studenti le competenze necessarie per analizzare i dati sperimentali e fare affermazioni causali nell'ambito dell'analisi dei dati.

È molto raccomandata una conoscenza di base della statistica e dell'inferenza statistica.

Lezioni teoriche ed esercitazioni.

Esame scritto con domande teoriche ed esercizi.

1. Review of Probability Distributions

2. Hypothesis Testing and Inference
• Sampling Distributions
• Tests of Hypothesis for a Single Sample
• Tests of Hypothesis for Two Samples
• Analysis of Variance (ANOVA)

3. Regression Modelling
• Classical Linear Regression Model (CLRM)
• Inferential aspects of CLRM
• Regression with Dummy Variables
• Regression with Binary Dependent Variable

4. Classical Randomized Experiments I
• The Potential Outcomes Framework
• Causal Directed Acyclic Graphs
• Assignment Mechanisms
• Bernoulli Trials
• Completely Randomized Experiments
• Stratified Randomized Experiments
• Paired Randomized Experiments

5. Classical Randomized Experiments II
• Fisher approach
• Neyman approach
• Regression-based Methods
• Covariates-adjustment

6. Design of Regular Assignment Mechanisms
• Unconfounded Treatment Assignment
• Estimating the Propensity Score
• Matching Procedures

English

• Review of Probability Distributions

• Hypothesis Testing and Inference

• Regression Modelling

• Classical Randomized Experiments

• Design of Regular Assignment Mechanisms

"Applied Statistics and Probability for Engineers" by Douglas Montgomery and George Runger.(Ch. 9-13)

"Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction" by Guido W. Imbens and Donald B. Rubin. (Part I, II and III)

This course introduces the principles of experimental research design with an emphasis on causal inference. We will learn how to evaluate if treatments have an effect on experimental units (e.g. clinical trials). We first explore paired hypothesis testing and regression analysis, and then cover in details the theory of statistical inference in randomized experiments. Causal inference for observational studies is also considered. The course is designed to equip students with the skills needed to analyze experimental data and make causal claims in data analytics.

Basic knowledge of statistics and statistical inference is highly recommended.

Theoretical lectures and exercises.

Written exam involving theoretical questions and exercises.

1. Review of Probability Distributions

2. Hypothesis Testing and Inference
• Sampling Distributions
• Tests of Hypothesis for a Single Sample
• Tests of Hypothesis for Two Samples
• Analysis of Variance (ANOVA)

3. Regression Modelling
• Classical Linear Regression Model (CLRM)
• Inferential aspects of CLRM
• Regression with Dummy Variables
• Regression with Binary Dependent Variable

4. Classical Randomized Experiments I
• The Potential Outcomes Framework
• Causal Directed Acyclic Graphs
• Assignment Mechanisms
• Bernoulli Trials
• Completely Randomized Experiments
• Stratified Randomized Experiments
• Paired Randomized Experiments

5. Classical Randomized Experiments II
• Fisher approach
• Neyman approach
• Regression-based Methods
• Covariates-adjustment

6. Design of Regular Assignment Mechanisms
• Unconfounded Treatment Assignment
• Estimating the Propensity Score
• Matching Procedures