- Docente: Silvia Pacei
- Credits: 12
- SSD: SECS-S/03
- Language: Italian
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: First cycle degree programme (L) in Business Administration (cod. 8405)
Learning outcomes
The aim of the course is to provide the knowledge of statistical methods used to collect, organize and analize data useful for the enterprise to take decisions in conditions of uncertainty. Besides, it provide a practical experience through computer lab with the SAS software.
Course contents
1. Statistics and the firm.
2.1. Business data base. Sample surveys. Sampling error. Random and non-random samples. Panel and rotating panel surveys. Choice of the sample dimension. How to calculate and correct sampling weights. Non sampling error.
2.2. Some official sources of data. The Istat and AcNielse consumer and expenditure survey. The Bank of Italy survey on income.
2.3. The data matrix.
3.1. Methods for forecasting industry demand and sales. Exogenous and endogenous methods for forecasting.
3.2 Multiple regression model. Basic assumptions. Parameters estimation and interpretation. OLS Estimators properties. Hypothesis testing for the model and for parameters. Residuals analysis. Comparison between nested models. The multicollinearity problem. The inclusion of qualitative explanatory variables in the model. Punctual and interval forecasting. Selection of explanatory variables.
3.3. Non linear regression models.
3.4. Examples .
4.1. Pricipal Component Analysis. Procedure. Choice of the number of components. Interpretation of components.
4.2. Examples.
5.1. The market segmentation. The distance-matrix.
5.2. "A priori" and "A posteriori" classification methods.
5.3. "A posteriori" methods: hierachical cluster analysis. Phases, methods, choice of the number of groups and description of groups.
5.4. "A posteriori" methods: non-hierachical cluster analysis. Phases, k-means method, choice of the number of groups and description of groups.
5.5. Examples.
6.1. Classification Trees. Binary and multiple segmantation using AID, CHAID e CART algorithms.
6.2. Examples.
Readings/Bibliography
Slides (for students attending the course) available one week before the first lesson on the web-site www2.stat.unibo.it/Pacei.
Brasini, Freo, Tassinari e Tassinari, Statistica aziendale e analisi di mercato, Il Mulino: Bologna, 2002, Capitoli: I (da 1.1 a 1.6); V (da 5.1 a 5.2); VI (da 6.1 a 6.2), VII (par. 1, 2, 3, 4, 6).
“Il campionamento statistico”, G. Cicchitelli, G. Montanari, A. Herzel, 1997, Il Mulino (parti relative alla costruzione dei pesi per vari disegni di campionamento).
Cap. 13 “La regressione lineare multipla”, scaricabile sul sito www.apogeonline.com/2006/libri/88-503-2357-3/ebook/2357-cap13.pdf, in Levine D.M., Krehbiel T., Berenson M.L., Statistica II ed., Apogeo: Milano.
“Introduzione all'econometria”, J.H. Stock e M.W. Watson (edizione italiana a cura di F. Peracchi), seconda edizione, 2009, Pearson Education, cap. 8.
Zani, Analisi dei dati statistici – Osservazioni multidimensionali, Giuffré: Milano, 2000. Capitoli 3 e 5.
“Analisi dei dati e data mining per le decisioni aziendali”, S. Zani e A. Cerioli, 2007, Giuffrè, cap. XI.
Teaching methods
Lectures and laboratory exercises.
Assessment methods
Report (written and oral) on the application of the statistica methods studied during the course to data obtained from sample surveys.
Office hours
See the website of Silvia Pacei