Overall objectives:

1 - O1. To provide general knowledge and understanding of the fundamental aspects of time series modelling and prediction;
2 - O2. Knowledge of the importance that prediction plays in supporting decision making within organisations;
3 - O3. The ability to do a critical, comparative and quantitative analysis of problems in the context of prediction;
4 - O4. The ability to use mathematic software in the analysis of data;
5 - O5. To develop skills of design, writing, presentation of results and developing teamwork.

Syllabus:

1 - P1. Introduction to time series analysis and forecasting (application examples, its importance; a general times series forecasting problem methodology).
2 - P2. Decomposition models (classical decomposition, trend analysis, analysis of seasonality); Time series analysis in time domain (correlogram; autocorrelation function) and in frequency domain (periodogram).
3 - P3. Optimal forecasting problem (performance measures).
4 - P4. Traditional forecasting models (exponential smoothing methods, deterministic linear parametric regression and autocorrelation models).
5 - P5. More advanced forecasting models (dynamic regression models).

Literature/Sources:

Stevenson, W.J , 1986 , Estatística aplicada à administração , , Editora Harbra
Makridakis, S., Wheelwright, S.C., e Hyndman, R.J , 1998 , Forecasting: methods and applications , John Wiley & Sons
Brockwell, P.J., e Davis, R.A , 1996 , Introduction to time series and forecasting , Springer, New York
Murteira, B.J.F., Muller, D.A., e Turkman, K.F , 1993 , Análise de sucessões cronológicas , McGraw-Hill, Lisboa
Montgomery, D.C., Jennings, C.L., e Kulahci, M. , 2008 , Introduction to time series analysis and forecasting , John Wiley & Sons

Assesssment methods and criteria:

Classification Type: Quantitativa (0-20)

Evaluation Methodology:
M1. Lectures; M2. Solving exercises; M3. Practical work in laboratory. Evaluation methodology: M4. Two mini-tests (1/4 of weight for each); M5. Practical work (1/2 of weight).