CHALLENGES FOR MULTILEVEL MODELS OF SCHOOL DISORDER: RESPONSE TO HOFFMANN AND JOHNSON* WAYNE N. WELSH PATRICIA H. JENKINS Temple University JACK R. GREENE Northeastern University It is an unusual commentary indeed when critics speculate about data analysis, findings, and conclusions, rather than reanalyzing any of our data (publicly available through the National Archive of Criminal Justice Data).l Hoffmann and Johnson (henceforth, zyxw HJ) have presented (in an earlier paper in this issue) an entirely different study with entirely different variables and entirely different hierarchical linear models (HLM). Surprisingly, they come up with much of the same conclusions regarding the dominance of individual-level predictors. Their cross-level interaction terms, uninformed by theory, account for negligible portions of explained variance. They present a rather narrow view of multilevel modeling that leaves important questions regarding theory and study design completely unaddressed. A number of omissions and errors further weaken their arguments. The gist of HJ’s argument is that we ignore cross-level interactions and overstate the primacy of individual-level explanatory variables. They imply a false standard with statements such as the following: “In particular, we are somewhat puzzled why they did not examine cross-level interactions” (19995). As Bryk and Raudenbush (19925) point out, HLM applications address three general research purposes: “improved estimation of effects within individual units (e.g., developing an improved estimate of a regression model for an individual school by borrowing strength from the fact that similar estimates exist for other schools), the formulation and testing of hypotheses about cross-level effects (e.g., how varying school size might affect the relationship between social class and academic achievement within schools), and the partitioning of variance and covariance components among levels (e.g., decomposing the correlation among set [sic] of student-level variables into within- and zy * The research reported here was supported by Grant 93-IJ-CX-0038from the zy US. Department of Justice, National Institute of Justice (NIJ). Opinions expressed here are those of the authors and not necessarily of the U.S. Department of Justice. National Archive of Criminal Justice Data. Available at http://www.icpsr. umich.edu/NACJD/home.html 1. CRIMINOLOGY VOLUME 38 NUMBER 4 2000 1289