Quality & Quantity 32: 15–29, 1998.
© 1998 Kluwer Academic Publishers. Printed in the Netherlands.
Multilevel Analysis of Repeated Measures Data
RIEN VAN DER LEEDEN
Department of Psychology, Unit of Psychometrics and Research Methodology, Faculty of Social
Sciences, Leiden University, P.O. Box 9555, 2300 RB Leiden, The Netherlands
Telephone: [+31] 71 5273763, Telefax: [+31] 71 5273619
Abstract. Hierarchically structured data are common in many areas of scientiﬁc research. Such data
are characterized by nested membership relations among the units of observation. Multilevel analysis
is a class of methods that explicitly takes the hierarchical structure into account. Repeated measures
data can be considered as having a hierarchical structure as well: measurements are nested within,
for instance, individuals. In this paper, an overview is given of the multilevel analysis approach to
repeated measures data. A simple application to growth curves is provided as an illustration. It is
argued that multilevel analysis of repeated measures data is a powerful and attractive approach for
several reasons, such as ﬂexibility, and the emphasis on individual development.
Key words: repeated measures, growth curve analysis, longitudinal data, multilevel analysis, hier-
archical linear model, hierarchical data.
Hierarchically structured data are frequently encountered in many areas of sci-
entiﬁc research. Such data are characterized by so-called “nested” membership
relations among the units of observation. For instance, in social and behavioural
science research employees are nested within departments, or sportsmen are nested
within teams. In biostatistics, birds are nested within breeding areas, or litters of
offspring are nested within animals, and so on. Classic examples of hierarchical
data are found in educational research: students are nested within classes, which
are nested within schools. Many other examples can be imagined.
Multilevel analysis comprises a class of methods employing hierarchical lin-
ear regression models. Such models explicitly take into account the hierarchical
structure of the data. Over the past 15 years, much progress has been made in
the development of multilevel analysis. Originating from educational research (see
e.g. Burstein, Linn & Capell, 1978; Tate & Wongbundit, 1983; De Leeuw & Kreft,
1986; Goldstein, 1987; Raudenbush, 1988; Bock, 1989), the technique is increas-
ingly being used by now in numerous research settings. Comprehensive textbooks
on theory and application of multilevel models include Goldstein (1987, 1995),
Bryk & Raudenbush (1992) and Longford (1993).