Summary of Course:
This course starts by reviewing the advantages of collecting and analysing longitudinal data. After discussing the various types of longitudinal data, we focus on panel data containing repeated measures. Topics will include: methods for exploring longitudinal data; alternative approaches for modelling repeated measures data for continuous and categorical responses with particular attention to population average and random effects models; and methods for handling complex survey designs, weights and non-response.
Course Objectives:
Course Content:
This course will include the following topics:
The methods will be illustrated and compared using analyses of attitudes and life satisfaction scores collected in the British Household Panel Survey. The course will have a strong practical emphasis, with regular computer sessions using STATA enabling participants to work through examples.
Target Audience:
The course is aimed at researchers who need to analyse longitudinal survey data, also called panel data or repeated measures data, especially those in the social, economic, educational and medical sciences. Participants should already be familiar with basic statistical theory, including inference, multiple linear regression and logistic regression. Participants may be researchers in the social sciences or may work in government, survey agencies, official statistics or the private sector.
Course Fee:
Thanks to continued ESRC funding we are able to offer this course at reduced rates as follows:
The course fee includes course materials, lunches and morning and afternoon refreshments. Travel and accommodation are to be arranged and paid for by the participant.
Course places are limited and early registration is strongly recommended.
Location and Accommodation:
The course will be held at the Southampton Statistical Sciences Research Institute, Building 39, University of Southampton, Southampton, SO17 1BJ. Participants are left to book their own accommodation according to individual needs.
Duration:
The course will begin with coffee and registration at 9.30 a.m. on the first day and finish at 5.00 p.m. on the last day.
Pre-requisite:
Participants on this course must have prior statistical knowledge covering inference, multiple linear and logistic regression for cross-sectional data (for example up to the level of the CASS course ‘Regression Methods').
The course will have a strong practical emphasis, with regular computing sessions, using STATA and real survey data, to enable participants to work through examples. Therefore, prior experience of analysing survey data using a statistical package is required. However, no prior knowledge of STATA will be assumed.
Course Materials:
Participants will receive written course notes.
The Instructors:
Details are to be confirmed.
Peter Smith is Professor of Social Statistics in the Social Statistics Division, School of Social Sciences, at the University of Southampton. He is also a member of the Southampton Statistical Sciences Research Institute. He has a BSc in Mathematics and an MSc and PhD in Statistics. His general research interests are in statistical modelling of social and medical data, including longitudinal data analysis. He has extensive experience in teaching short courses, including several courses for CASS on longitudinal data analysis.
Ann Berrington is a Reader in Social Statistics in the Social Statistics Division, School of Social Sciences, at the University of Southampton. She is also a member of the Southampton Statistical Sciences Research Institute. She has a BSc in Human Sciences, an MSc in Medical Demography and a PhD in Social Statistics. Her general research interests are in demography. She has wide-ranging experience in handling and analysing longitudinal survey data. She has also extensive experience in teaching short courses, including several courses for CASS on longitudinal data analysis.
Preparatory Reading:
For participants who wish to do background reading, the following references may be useful. Please note that although reading is optional, participants who have little statistical background in longitudinal or multilevel modelling are strongly advised to look at some of these references.