Time Series Prediction

Course guarantor:

Lecturer:

Tutor:

Supervisor:

Department of Transport Telematics

Synopsis:

Introduction to time series prediction, prediction role in information society, basics of quantitative prediction.

Model performance evaluations, descriptive statistics, MAE, MAPE, RMSE, naive predictions, general formulation of the loss prediction function.

Computing and programming in environment R.

Regression models, basics of linear regression, simple regression.

Multiple regression, statistical tests of linear dependence, selection of input variables, prediction by regression methods.

Generalized linear model (GLM) and its use in prediction problems.

GAM models for predictions and estimates in complex prediction tasks.

Autoregressive processes, model order estimation.

Box-Jenkins methodology, process stationarity.

Regression models with random effects, design of data collection for identification of prediction model.

State-space models, their identification (Kalman filter), applications in forecasting.

Examples of prediction systems

Design of own prediction models.

Consultation of practical problems motivated by students

Requirements:

Syllabus of lectures:

Syllabus of tutorials:

Study Objective:

Study materials:

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans: