## MAS6002 Statistical Laboratory

Note: This is an old module occurrence.

You may wish to visit the module list for information on current teaching.

 Both semesters, 2014/15 20 Credits Lecturer: Dr Kevin Walters uses MOLE Reading List Aims Outcomes Teaching Methods Assessment Full Syllabus

This module starts in Intro Week with a speedy review of the basic background expected for the MSc. The module will then introduce students to a range of statistical and programming techniques and give practice in their implementation and interpretation using the software R. It aims to help students develop the knowledge and experience to select and use appropriate techniques for a variety of problems. The emphasis will be on practical application of techniques and knowledge of their scope rather than development of theoretical underpinnings (which will be met in other units). Areas to be covered include: exploratory data analysis, simple checks on data, density estimation, simulation, programming and optimization.

There are no prerequisites for this module.
No other modules have this module as a prerequisite.

## Outline syllabus

• Introductory theory (Probability, Likelihood, Basic Statistics)
• Introduction to R.
• EDA and simple checks on data in R, R functions. R objects.
• Programming in R.
• Simulation and optimization in R
• Researching modern statistical techniques: independent study.

## Aims

• To review basic theoretical material.
• To introduce students to the software R and give practice in its use.
• To give practice in applying methods and interpreting results from them.
• To help students develop the knowledge and experience necessary to select and use appropriate statistical techniques for a variety of problems.
• To help students develop skill in the preparation of technical documents.

## Learning outcomes

• demonstrate capability in basic introductory theory;
• appreciate the breadth of statistical methodology;
• use R to apply the methods dealt with in the course;
• write simple functions and programs in R;
• find out independently about further areas of methodology;
• appreciate the main ideas in at least one of: tree-based methods, robust methods, local regression methods, spatial data analysis, non-linear regression techniques and generalized additive modelling; and have some acquaintance with at least three of the others;
• prepare technical documents.

## Teaching methods

Examples classes and computer practice in the PC Laboratories; on-line discussion. Feedback on assignments. Group work. Student presentations.

No lectures, no tutorials, 18 practicals

## Assessment

Five continuously assessed assignments (one set of problems, three reports, and one presentation).

## Full syllabus

N.B `sessions' are 2hrs.

• Introductory Material (6 sessions)
• Introduction to R. (2.5 session)
• R and EDA: simple checks on data (2 sessions)
• Writing R functions (1 session)
• Working with tables, programming in R objects (3 sessions)
• Using R to solve problems in linear models. (2 sessions)
• Optimization and Simulation in R. (4 sessions)
• Researching modern statistical techniques: tree-based methods, robust methods, local regression methods, spatial data analysis, non-linear regression techniques and generalized additive modelling. (1 session plus independent study)