Statistical Modelling 6 (2006), 251263
Modelling repeated ordinal reports from multiple
informants
Ian Plewis
Bedford Group for Lifecourse and Statistical Studies,
Institute of Education,
University of London,
20 Bedford Way,
London WC1H 0AL
U.K.
eMail:
i.plewis@ioe.ac.uk
Frank Vitaro and Richard Tremblay
G.R.I.P.,
University of Montreal
Canada
Abstract:
Cross-informant associations tend to be low for reports of
children’s behaviours at one point in
time. The paper extends the literature on multiple
informants using data from a well-known longitudinal
study of Quebec, Canada, boys to show how to estimate
associations between repeated teachers’ and selfreports
of aggressive behaviour. These associations, for both
level and change, are derived from multilevel
models for repeated measures of variables best treated
as ordered categories. The ordering is represented by
sets of continuation ratios, change by linear and
quadratic functions of age, and themultivariate models are
estimated using penalized quasi-likelihood. The analyses
also incorporate a risk variable: socio-economic
status (SES). The correlations between estimates of the
growth parameters for the two sets of reports tend
to be rather small and smaller than the cross-informant
associations for levels. SES is associated with levels
of aggression, more so for teacher reports than for
self-reports, but not with the decline in aggression
with age.
Keywords:
continuation ratios; multilevel models; multiple informants;
psychological development; repeated measures; risk variables
Downloads:
Example
data in zipped archive
back