Dw. Osgood et Gl. Smith, APPLYING HIERARCHICAL LINEAR MODELING TO EXTENDED LONGITUDINAL EVALUATIONS - THE BOYS-TOWN FOLLOW-UP-STUDY, Evaluation review, 19(1), 1995, pp. 3-38
Longitudinal research designs with many waves of data have the potenti
al to provide a fine-grained description of program impact, so they sh
ould be of special value for evaluation research. This potential has b
een illusive because our principal analysis methods are poorly suited
to the task. We present strategies for analyzing these designs using h
ierarchical linear modeling (HLM). The basic growth curve model found
in most longitudinal applications of HLM are not well suited to progra
m evaluation, so we develop more appropriate alternatives. Our approac
h defines well-focused parameters that yield meaningful effect-size es
timates and significance tests efficiently combining all waves of data
available for each subject. These methods do not require a uniform se
t of observations from all respondents. The Boys Town Follow-Up Study,
an exceptionally rich but complex data set, is used to illustrate our
approach.