Checking date: 23/04/2019


Course: 2019/2020

Time series analysis and forecasting
(17238)
Study: Master in Big Data Analytics (322)
EPI


Coordinating teacher: GALEANO SAN MIGUEL, PEDRO

Department assigned to the subject: Department of Statistics

Type: Compulsory
ECTS Credits: 3.0 ECTS

Course:
Semester:




Students are expected to have completed
Statistical modelling for data analysis Mathematics for data analysis
Competences and skills that will be acquired and learning results.
Basic competences To have and to include/understand knowledge that contribute to a base or opportunity of to be original at the development and/or application of ideas, to slight in an investigation context That the students know to apply to the acquired knowledge and their capacity of resolution of problems in new surroundings or little known within ampler contexts (or you will multidiscipline) related to their area study That the students are able to integrate knowledge and to face the complexity to formulate judgments from a information that, incomplete or being limited, includes reflections on tie the social and ethical responsibilities to the application of its knowledge and judgments That the students have the learning abilities that allow them to continue studying of a way that will be to be in great homing or independent measurement. General competitions To apply the theoretical foundations of the collection techniques , storage, treatment and presentation of information, specially for great volumes of data, as it bases for the development and adaptation of these techniques to concrete problems To identify different techniques to store, to talk back and to distribute great amounts of data, and to differentiate them based on its theoretical and practical characteristics To identify the techniques of analyses of data but adapted each problem and knowledge to apply them for the analysis, design and solution of such To obtain practical and efficient solutions for problems of treatment of great volumes of data, as much individually as in equipment To synthesize the obtained conclusions of these analyses and to as much present/display them of clear and convincing way in bilingual surroundings (Spanish and English) in writing as orally To be able to generate new ideas (creativity) and to anticipate new situations, in the contexts of the analysis of data and the decision making To use abilities for the work in equipment and to be related to others of independent form Specific competitions To use the basic results of inference and regression like foundation for advanced methods of prediction and classification To identify and to select the suitable software tools for the treatment of great amounts of data To use advanced statistical procedures for the treatment of great volumes of data in areas like the estimation, the inference, the prediction or the classification, as well as the way to apply them of efficient form To correctly identify the kind of statistical problem corresponding to certain objectives and data To know how to design systems for the processing of the data, from the obtaining and initial filtrate of such, its statistical analysis, to the presentation of the final results To use techniques and usable tools of operations research with massive data in procedures for its analysis, visualization of its results or within systems of support to decisions
Description of contents: programme
1. Introduction. 1.1 What can be forecast? 1.2 Forecasting, planning and goals. 1.3 Forecasting data and methods. 1.4 Forecasting basic toolbox. 2. Time series decomposition. 2.1 Time series components. 2.2 Moving averages. 2.3 Classical decomposition. 2.4 ARIMA decomposition. 2.5 STL decomposition. 2.6 Forecasting with decomposition. 2.7 Exponential smoothing: linear, exponential, damped, seasonal trend methods. 3. ARIMA models. 3.1 Stationarity and differencing. 3.2 Backshift notation 3.3 Autoregressive models. 3.4 Moving average models. 3.5 Non-seasonal ARIMA models. 3.6 Estimation and order selection. 3.7 Forecasting. 3.8 Seasonal ARIMA models. 3.9 ARIMA vs ETS. 4. Advanced forecasting methods. 4.1 Dynamic regression models. 4.2 Vector autoregressions. 4.3 Neural network models. 4.4 Forecasting hierarchical or grouped time series. 5. Univariate volatility models. 5.1 GARCH models. 5.2 Statistical properties. 5.3 Estimating parameters and volatilities. 5.4 Some examples. 6. Multivariate volatility models. 6.1 Multivariate GARCH models. 6.2 Estimation methods and some examples.
Learning activities and methodology
Formative activities: Theory classes Practical classes Computing practicals Individual student work Teaching methodology: Theory classes (with computing and audiovisual technology) presenting the main parts of the course and the associated bibliography. Critical reading of texts recommended by the course teachers. Practical and computing classes designed by the course teachers for group and individual work. Group and individual homework projects.
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100
Basic Bibliography
  • Robert H. Shumway, David S. Stoffer. Time series analysis and its applications. Springer. 2016
  • Ruey S. Tsay. Analysis of Financial Time Series. Wiley. 2010
  • Ruey S. Tsay. An Introduction to Analysis of Financial Data with R. Wiley. 2013

The course syllabus and the academic weekly planning may change due academic events or other reasons.