About | HeinOnline Law Journal Library | HeinOnline Law Journal Library | HeinOnline

LOG IN
LOG IN


20 J. Quantitative Criminology 1 (2004)

handle is hein.journals/jquantc20 and id is 1 raw text is: Journal of Quantitative Criminology, Vol. 20, No. 1, March 2004 ((2004) Methodological Sensitivities to Latent Class Analysis of Long-Term Criminal Trajectories Elaine P. Eggleston,'3 John H. Laub,' and Robert J. Sampson2 A recent and growing body of research has employed a semiparametric group- based approach to discover underlying developmental trajectories of crime. En- thusiasm for such latent class models has not been matched with robustness and sensitivity analyses to determine how conclusions from the method vary accord- ing to fundamental methodological problems that inhere in criminological data. Using a sample of 500 delinquent boys and their official crime counts from ages 7 to 70, this paper systematically addresses how three concerns in longitudinal research (a) length of follow-up, (b) the inclusion of exposure time (incarcera- tion), and (3) data on involuntary desistance through death influence our inferences about developmental trajectories. While there is some evidence of stability, a comparison of group number, shape, and group assignment across varying conditions indicates that all three data considerations can alter trajec- tory attributes in important ways. More precisely, longer-term data on offending and the inclusion of incarceration and mortality information appear to be key pieces of information, especially when analyzing high-rate offending patterns. KEY WORDS: semiparametric group-based method; sensitivity analysis; long- itudinal research methods; trajectories. 1. INTRODUCTION Debates about continuity and change in offending over the life course have animated criminology over the last decade. There are several methods currently employed to estimate developmental trajectories and within- individual change in a longitudinal perspective, including hierarchical linear modeling, growth curve analysis, and semiparametric mixture models, to name a few (for a discussion on modeling longitudinal trajectories see, e.g., Bushway et al., 1999; Raudenbush, 2001). This paper focuses on the Department of Criminology and Criminal Justice, 2220 LeFrak Hall, University of Maryland, College Park, MD 20742-8235. 2Department of Sociology, Harvard University, Cambridge, MA. 3 To whom correspondence should be addressed: E-mail: eeggleston@crim.umd.edu 0748-4518/04/0300-0001/0 © 2004 Plenum Publishing Corporation