Module ST3007: Applied Forecasting/Multivariate Data Analysis
 Credit weighting (ECTS)
 10 credits
 Semester/term taught
 Michaelmas term 2012  Applied Forecasting
 Hilary term 2013  Multivariate Analysis
 Contact Hours
 22 weeks, 3 lectures including tutorials per week
 Lecturers
 Prof. Rozenn Dahyot (Statistics), Prof. Brett Houlding (Statistics)
 Learning Outcomes
 Applied Forecasting:
 On successful completion of this module, students should be able to:
 Define and describe the different patterns that can be found in times series and propose the methods that can be used for their analysis;
 Program, analyse and select the best model for forecasting;
 Interpret output of data analysis performed by a computer statistics package;
 Multivariate Analysis:
 On successful completion of this module, students should be able to:
 Define and describe various classical dimension reduction techniques for multivariate data;
 Implement clustering and/or classification algorithms and assess and compare the results;
 Interpret output of data analysis performed by a computer statistics package.
 Module Content
 Applied Forecasting:

 HoltWinters Algorithms for forecasting
 ARIMA models for time series modelling;
 Forecast and uncertainty using confidence intervals.

 Principal Components Analysis;
 Multidimensional Scaling;
 Factor Analysis;
 Hierarchical and Iterative Clustering;
 KNearest Neighbours;
 Discriminant Analysis;
 Logistic Regression
 Module Prerequisite
 Recommended Reading
 Applied Forecasting:

 Chatfield, C. (2004) The Analysis of Time Series, 6th edition, Chapman and Hall;
 Makridakis, A., S.C. Wheelwright and R.J. Hyndman (1998) Forecasting: Methods and Applications, 3rd edition;
 Multivariate Analysis:

 Introductin to Multivariate Analysis, C. Chatfield and A. Collins, Chapman & Hall
Assessment Detail
 This module will be examined in a 3 hour examination in Trinity term. Continuous assessment will contribute 30% to the final grade for the module at the annual examination session.