Programma

The course covers econometrics and statistical modeling, beginning with a review of matrix algebra and estimation theory. It introduces the classical linear regression model, exploring its assumptions, parameter estimation via Ordinary Least Squares (OLS), and the Gauss-Markov theorem.
Further topics include maximum likelihood estimation, hypothesis testing, and techniques to address violations of classical model assumptions (heteroskedasticity, autocorrelation, multicollinearity, measurement errors). The course discusses generalized least squares, diagnostic tests, and instrumental variable estimators.
It continues with linear forecasting, model misspecification (omitting relevant or including redundant variables), and the use of dummy variables to test regression stability (Chow test). Measures of model fit such as R², AIC, and BIC are introduced, along with distributed lag models.
The final part of the course focuses on panel data models (fixed and random effects) and time series analysis, covering descriptive aspects, structural components (trend, cycle, seasonality), and stochastic models (AR, MA, ARMA), emphasizing stationarity and invertibility.

Testi Adottati

Introduzione all’econometria
James H. Stock - Mark W. Watson
Ed. Pearson

Econometria
Marno Verbeek
Ed. Zanichelli

Lecturer's Notes

Modalità Valutazione

Oral exam on the course topics

Programma

The course covers econometrics and statistical modeling, beginning with a review of matrix algebra and estimation theory. It introduces the classical linear regression model, exploring its assumptions, parameter estimation via Ordinary Least Squares (OLS), and the Gauss-Markov theorem.
Further topics include maximum likelihood estimation, hypothesis testing, and techniques to address violations of classical model assumptions (heteroskedasticity, autocorrelation, multicollinearity, measurement errors). The course discusses generalized least squares, diagnostic tests, and instrumental variable estimators.
It continues with linear forecasting, model misspecification (omitting relevant or including redundant variables), and the use of dummy variables to test regression stability (Chow test). Measures of model fit such as R², AIC, and BIC are introduced, along with distributed lag models.
The final part of the course focuses on panel data models (fixed and random effects) and time series analysis, covering descriptive aspects, structural components (trend, cycle, seasonality), and stochastic models (AR, MA, ARMA), emphasizing stationarity and invertibility.

Testi Adottati

Introduzione all’econometria
James H. Stock - Mark W. Watson
Ed. Pearson

Econometria
Marno Verbeek
Ed. Zanichelli

Lecturer's Notes

Modalità Valutazione

Oral exam on the course topics

Programma

The course covers econometrics and statistical modeling, beginning with a review of matrix algebra and estimation theory. It introduces the classical linear regression model, exploring its assumptions, parameter estimation via Ordinary Least Squares (OLS), and the Gauss-Markov theorem.
Further topics include maximum likelihood estimation, hypothesis testing, and techniques to address violations of classical model assumptions (heteroskedasticity, autocorrelation, multicollinearity, measurement errors). The course discusses generalized least squares, diagnostic tests, and instrumental variable estimators.
It continues with linear forecasting, model misspecification (omitting relevant or including redundant variables), and the use of dummy variables to test regression stability (Chow test). Measures of model fit such as R², AIC, and BIC are introduced, along with distributed lag models.
The final part of the course focuses on panel data models (fixed and random effects) and time series analysis, covering descriptive aspects, structural components (trend, cycle, seasonality), and stochastic models (AR, MA, ARMA), emphasizing stationarity and invertibility.

Testi Adottati

Introduzione all’econometria
James H. Stock - Mark W. Watson
Ed. Pearson

Econometria
Marno Verbeek
Ed. Zanichelli

Lecturer's Notes

Modalità Valutazione

Oral exam on the course topics

Programma

The course covers econometrics and statistical modeling, beginning with a review of matrix algebra and estimation theory. It introduces the classical linear regression model, exploring its assumptions, parameter estimation via Ordinary Least Squares (OLS), and the Gauss-Markov theorem.
Further topics include maximum likelihood estimation, hypothesis testing, and techniques to address violations of classical model assumptions (heteroskedasticity, autocorrelation, multicollinearity, measurement errors). The course discusses generalized least squares, diagnostic tests, and instrumental variable estimators.
It continues with linear forecasting, model misspecification (omitting relevant or including redundant variables), and the use of dummy variables to test regression stability (Chow test). Measures of model fit such as R², AIC, and BIC are introduced, along with distributed lag models.
The final part of the course focuses on panel data models (fixed and random effects) and time series analysis, covering descriptive aspects, structural components (trend, cycle, seasonality), and stochastic models (AR, MA, ARMA), emphasizing stationarity and invertibility.

Testi Adottati

Introduzione all’econometria
James H. Stock - Mark W. Watson
Ed. Pearson

Econometria
Marno Verbeek
Ed. Zanichelli

Lecturer's Notes

Modalità Valutazione

Oral exam on the course topics