STATISTICS SEMINAR
DEPT OF MATHEMATICS, UNIVERSITY OF MANCHESTER
This is part of the second semester seminar programme of the
Manchester Centre for Statistical Science.
On Wednesday 10th February 1999 at 4.00 p.m.
Venue: Room 1.09
Mathematics Building
The University of Manchester
Oxford Road
Manchester
Title: Handling missing data in diaries of alcohol consumption
Speaker: Nicholas T. Longford, Department of Medical Statistics,
De Montfort University, Leicester
with
Margaret Ely, Rebecca Hardy, and Michael Wadsworth
Department of Epidemiology and Public Health, University College, London
Missing data can rarely be avoided in large-scale studies in which
subjects are requested to complete questionnaires with many items.
Analyses of such surveys are often based on records with no missing
items, resulting in loss of efficiency and, when data are missing not
at random, in bias.
This paper applies the method of multiple imputations to handle
missing data in an analysis of alcohol consumption of the subjects in
the National Study of Health and Development. The outcomes studied are
derived from the entries in diaries of food and drink intake over seven
designated days. Background variables and other responses related to
alcohol consumption and associated problems are used as collateral
information. In conventional analyses, subpopulation means of
quantities of alcohol consumed are compared. Since we are interested
in the harmful effects of alcohol, we make inferences about the
percentages of those who consume more than a given quantity of net
alcohol. We assess the contribution to the analyses made by
the incomplete records and outline a more integrated application of
multiple imputations in large-scale longitudinal surveys.
The talk will be followed by tea and biscuits. All those who are
interested are very welcome to attend.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|