background to the PEAS project

Download Report

Transcript background to the PEAS project

Background to PEAS project
Gillian Raab
Professor of Applied Statistics
Napier University
ESRC research methods programme
• foster work that directly enhances methodological
knowledge or improves and advances quantitative
and qualitative methods;
• encourage and support the dissemination of good
practice, including the enhancement of training
programmes and training materials for the
research community;
http://www.ccsr.ac.uk/methods/
UK expertise in surveys
• Universities have less than in NA or Europe
• Most of it lies in survey organisations
• The ESRC makes lots of data available via their
survey archive
• But there is limited expertise in universities on the
best ways of analysing this
• Government departments are also major users of
these national survey data sets
Survey design and analysis
• Big surveys are usually complicated
• The design is intended to enable the survey to get
accurate and precise results
• The survey design ought to be reflected in the
analysis
• Usual statistical methods (e.g. t-tests, chi squared
tests) don’t allow for this
• But there are statistical methods which can
• Developed 1950s to the present
PEAS project
•
•
•
•
I was not analysing surveys properly
Started to try to improve while doing some contract work
Got good advice from Susan Purdon
Found that survey software was beginning to become more
generally available but was hard to use
• Applied to the ESRC with Susan to get funding to provide
web based training material
• Joined by Kathy Buckner for web and HCI expertise
• Now ably assisted by Iona Waterston, web designer
PEAS aims
• to develop a web-based resource which will take
the survey analyst through exemplars of the use of
different methods that are currently available for
the analysis of complex surveys
• to hold a series of workshops aimed at researchers
who analyse survey data.
• The web site will also contain a guide to survey
design and analysis
Design/analysis links
Decide on a design
Set up and run the survey and get data
Analyse the results
Evaluate their bias and precision
Workshop 1 aims
• For us to get a first impression of how people will
use the material on the web site
• To find out what people might like to find on the
web site
• To get feedback on the design and navigation
aspects of the site
• We are still very much under development, so not
everything will work yet
• To give the participants some information about
survey design and analysis