# Applied Statistics and Econometrics

Applied Statistics and Econometrics Bacher of Science in Business & Economics University of Rome { TorVergata Fall a.y. 2016/2017 Chiara Perricone cpe...

Applied Statistics and Econometrics Bacher of Science in Business & Economics University of Rome – TorVergata Fall a.y. 2016/2017

Chiara Perricone [email protected] This course is designed for the students of the Bachelor of Science in Business and Economics. The aim of this course is to provide an introduction to the practice of econometrics. While both theoretical and practical aspects will be covered, emphasis will be on intuitive understanding. Theoretical methodologies will be presented followed by an extensive application in R (https://www.r-project.org/).

Syllabus Review of Descriptive statistics Data types, exploratory analysis (graphics and summary statistics) for univariate and multivariate data.

Review of probability Main definitions (random variable, cdf and pdf), expected value and moments, notable distributions (Normal, standard normal, chi-square, F, T), convergences (in probability, in distribution and almost surely), Weak Law of Large Number, Central Limit Theorem.

Review of Statistical inference Point estimate, hypothesis testing, confidence interval.

Bivariate linear regression Coefficients estimate and interpretation (quantitative and binary independent variable), model evaluation, hypothesis testing, homoskedastic and heteroskedastic errors.

Omitted variable bias and Multivariate Linear Regression Coefficient estimates and interpretation (quantitative, binary and categorical independent variable), measure of fit, hypothesis testing (simple hypothesis test on a single coefficient and joint hypothesis tests on multiple coefficients).

Non Linear regression Why non linear relation?, nonlinear functions of one variable: log–linear, linear–log and log–log models

Time series – Univariate Stationarity and stationarized process, autocovariance and autocorrelation functions, autoregressive and moving average models (AR(p), MA(q) and ARMA(p,q)), Wald decomposition theorem, estimate (Yule Walker equations, maximum likelihood and OLS), lag length selection, forecast, impulse response functions.

Time series – Multivariate VAR model, estimation, forecast and impulse response functions.

1

Reference Materials • Main: Stock, James H. and Mark W. Watson, Introduction to Econometrics, Addison Wesley. Roughly chapter from 1 to 9, 14, 16. • Alternative: Jeffrey Wooldridge, Introductory Econometrics – A modern approach, South Western. Roughly chapter from 1 to 12, 18.

Course materials (slides, exercises and R codes) available at: cperricone.wordpress.com ⇒ Applied Statistics and Econometrics – TorVergata ⇒ Password: ase 2016

Assessment method • Written test (multiple choice): 70% of final grade. • 3 mandatory Problem sets (team work) carried out during the course: 30% of final grade. Problem set deadline: – PS1: due by 24/10, midnight – PS2: due by 21/11, midnight – PS3: due by 01/12, midnight Please carefully read ‘How to write and submit your solution to Problem Sets’.

2