Part 1 (3 ECTS. Prof. Laura Grassini). Simple and multiple linear regression. Least squares method (LS). Non-linear models in variables and variables transformations. Dummy regressors. Specification errors. Introduction to simultaneous equations models.
Part 2 (3 CFU. Prof. Lucia Buzzigoli). Statistical models for economic time series analysis: decomposition methods; moving averages; AR, MA, ARMA, ARIMA and seasonal ARIMA models.
Dougherty C., Introduction to econometrics. 5a ed., 2016, Oxford University Press.
Lecture notes and teaching materials are available on the Moodle platform.
Learning Objectives
Provide the methodological basis of econometric models and of time series models.
Present some free open-source software for the realization of simple empirical analyses.
At the end of the course, the student has acquired knowledge of the use of uni-equational econometric models and core time series methods for the analysis of univariate economic series. He/she is able to perform his/her own analysis of economic datasets using an open-source software.
Prerequisites
Statistics (undergraduate level)
Teaching Methods
Classroom lectures and computer labs.
Further information
Slides, teaching material and more detailed information on the course are available on the Moodle platform (http://e-l.unifi.it/). To access the course students have to send an e-mail request to the teachers (only e-mail sent by the UNIFI address will be accepted).
Type of Assessment
Oral examination with discussion of homework exercises.
Course program
Part 1.
1) Review of estimation theory and hypothesis testing. Variance, covariance and correlation.
2) Simple linear regression (1). Ordinary least squares (OLS). Properties of OLS estimates. R-square. Distribution hypotheses on the stochastic component of the model. Properties of least squares estimators. Test of hypotheses on model parameters.
3) Multiple linear regression. Derivation and interpretation of the coefficients. Test of hypotheses on model parameters. Multicollinearity.
4) Non-linear models in the variables. Variable transformations (example: Cobb-Douglas analytical form for representing production function). Quadratic and interactions effects.
5) Dummy regressors.
6) Specification errors in the explanatory variables (omission of variable, inclusion of irrelevant variables) and heteroskedasticity.
7) Introduction to stochastic regressors and simultaneous equations models.
Use of open source software (R. Gretl).
Part 2.
Time series analysis in economics.
Introductory univariate time series analysis with linear methods.
Exploratory analysis: plots, summary statistics, transformations (logs, differencing, index numbers).
Time series decomposition. Time series components (trend, cycle, seasonal component and error).
Moving averages. Census I seasonal decomposition.
AR, MA, ARMA, ARIMA and SARMA models. Box-Jenkins methodology.
Classroom lectures are accompanied by computer labs.