Multilevel Modelling Using MLwiN

Dates: Tuesday 8th and Wednesday 9th November 2011

Times: 9.30am to 4.30pm

Course Leaders: Dr Helen Brown (University of Edinburgh and AQMEN) and Rebecca Pillinger (University of Bristol and LEMMA)

Location: WISERD Training Rooms, 46 Park Place, Cardiff University

Overview

This course will explore the use of multilevel models and will emphasise their practical application in social sciences.  The main focus will be on multilevel models for continuous, binary and multinomial outcomes, with shorter introductory sessions on models for ordinal and count outcomes.  Analyses will be illustrated using MLwiN (a package dedicated to multilevel modelling available free to academics) and lectures will be combined with practical sessions in order to reinforce concepts.

Who should attend?

This course is directed at people working in social sciences who already have a good understanding of regression methods and wish to extend their knowledge to multilevel models.

Why attend?

Multilevel models are becoming an increasingly popular method of analysis and there are many situations where greater insight is obtained compared to simpler methods such as ANOVA or multiple regression. Potential advantages include:

• a wider inference: for example, in a study of school attainment, results can be related to a population of schools rather than just those assessed;
• more appropriate estimates of standard errors, by taking account of the fact that observations within the same group tend to be positively correlated with each other: for example, pupils in the same school tend to be more similar than pupils in different schools;
• more appropriate mean estimates, with the risk of spurious outlying results for small groups reduced;
• a more efficient analysis with smaller standard errors particularly when there are few observations per group;
• avoidance of problems caused by missing outcomes: this is an advantage in longitudinal studies, for example panel studies, where there are often dropouts;
• use of more appropriate variances and correlations: for example, in a longitudinal analysis the correlation between observations on the same person may become less for measurements that are further apart in time.

A full timetable for the event can be found here.

Fee Information

Workshop fee per day:

UK Registered Postgraduate Student - £30
Staff at Any UK Higher Education Institution - £60
ESRC Funded Researcher - £60
Registered Charity or Public Sector Worker - £60
Other - £220

All fees include event materials, lunch, morning and afternoon tea. They do not include travel and accommodation costs.

A booking form for this event can be found by clicking here.

For further information please contact WISERD.events@cardiff.ac.uk