|
General information |
Course unit name: Forecasting Methods
Course unit code: 363676
Academic year: 2025-2026
Coordinator: Jordi Pons Novell
Department: Department of Econometrics, Statistics and Applied Economics
Credits: 6
Single program: S
|
Estimated learning time |
Total number of hours 150 |
|
Face-to-face and/or online activities |
60 |
|
- Lecture with practical component |
Face-to-face |
45 |
|||
|
- Problem-solving class |
Face-to-face |
15 |
|||
|
Supervised project |
40 |
|
Independent learning |
50 |
|
Recommendations |
|
Although the content of this subject can stand in isolation, students should have previously taken Statistics I and II (which are second-year subjects in the recommended four-year degree pathway). Students are recommended to take (or to have already taken) the course in Business Econometrics, as this will help them better understand and assimilate the concepts covered in the course dedicated to Forecasting Methods. |
|
Competences / Learning outcomes to be gained during study |
| - |
To be able to use ICT in professional practice. |
| - |
To be able to make financial and business decisions, taking into account the current economic situation. |
| - |
To use basic quantitative methods and instruments to obtain and analyse company information and its socioeconomic environment, in accordance with the characteristics of the available information. |
|
Learning objectives |
|
Referring to knowledge The general objective of this course is to outline some of the most commonly used methods for making predictions of economic time series solely on the strength of past information on the variable being studied. |
|
Teaching blocks |
Block 1. Introduction
Unit 1. Introduction
1.1. Forecasting and economic and business decisions
1.2. Classification of prediction methods
1.3. Prediction and assessment of predictive capacity
Block 2. Classical time series methods
Unit 2. Deterministic models (I)
2.1. Definition of time series and components
2.2. Prediction using non-trend models
2.3. Prediction with trend models
Unit 3. Deterministic models (II)
3.1. Analysis of the seasonal component
3.2. Prediction with non-trend models and seasonal component
3.3. Prediction with trend models and seasonal component
Block 3. Stochastic time series methods: Box–Jenkins methodology
Unit 4. Stochastic methods for time series (I): basic concepts
4.1. Stochastic processes
4.2. Concepts of stationarity and ergodicity
4.3. Autocovariance and autocorrelation functions
4.4. Elementary models: white noise and random path
Unit 5. Stochastic models for time series (II): linear models
5.1. Autoregressive models (AR)
5.2. Moving average models (MA)
5.3. Mixed models (ARMA)
5.4. Non-stationary processes. Integrated models (ARIMA)
5.5. Seasonal models (SARIMA)
Unit 6. Stochastic models for time series (III): Box–Jenkins methodology
6.1. Identification of models
6.2. Parameter estimation
6.3. Model validation
6.4. Point and interval prediction
6.5. Intervention analysis
|
Teaching methods and general organization |
|
Since the learning objectives require a considerable amount of practical work, the general teaching methodology involves a combination of theoretical concepts and a specific focus on their practical applicability. Therefore, the following activities are undertaken: |
|
Official assessment of learning outcomes |
|
Continuous assessment
Examination-based assessment Students unable to commit to the demands of continuous assessment may opt for the single mode. To pass the subject, students must sit a single examination, worth 100% of the final grade. This examination takes place during the official examination period as established by the Academic Board. The written examination assesses the theoretical and practical aspects of the course. Students must demonstrate the knowledge, skills and competences they have acquired during the course. |
|
Reading and study resources |
Check availability in Cercabib
Book
AZNAR, Antonio; TRÍVEZ, Francisco J. Métodos de predicción en economía (Volumen 1). Barcelona: Ariel, 1993.
DIEBOLD, Francis X., Elements of forecasting. New York: South-Western, 2007.
HYNDMAN, Rob; ATHANASOPOULOS, George. Forecasting. Principles and practice. Melboure: OTexts, 2021.
MARTÍN PLIEGO, Francisco Javier. Introducción a la estadística económica y empresarial: teoría y práctica. 3a ed. Madrid: Thomson, 2011.
PEÑA, Daniel. Análisis de Series Temporales. Madrid: Alianza Editorial, 2010.
PULIDO, Antonio; LÓPEZ, Ana María. Predicción y simulación aplicada a la economía y gestión de empresas. Madrid: Pirámide, 1999.
SPIEGELHALTER, David. El arte de la estadística. Madrid: Capitán Swing, 2023.
URIEL JIMENEZ, Ezequiel. Análisis de datos: series temporales y análisis multivariante. Madrid: AC, 1995.
URIEL JIMENEZ, Ezequiel; PEIRÓ, Amado. Introducción al análisis de series temporales. Madrid: AC, 2005.