Type of Document	Thesis
Author	Gaitanis, Jason Andrew
Author's Email Address	gaitanisj@aol.com
URN	etd-11172003-200401
Title	An Application of Hierarchical Generalized Linear Modeling (HGLM) Techniques for Investigation into the Effects of Co-Mingling Delinquent and Non-Delinquent Youth in Juvenile Justice Prevention Programs in Florida
Degree	Master of Science
Department	Educational Psychology and Learning Systems, Department of
Advisory Committee	Advisor Name Title Richard Tate Committee Chair Akihito Kamata Committee Member Albert Oosterhof Committee Member
Keywords	Delinquency Prevention Juvenile Justice Florida Hierarchical Generalized Linear Modeling Hglm Co-Mingling
Date of Defense	2003-11-05
Availability	unrestricted
Abstract Current literature in the social sciences largely ignores important nested data structures when seeking to explain or interpret effects of independent variables on outcomes of interest. This is particularly true when the outcome of interest is dichotomous. A set of demonstration data is analyzed using HGLM software, and a set-by-step description of the procedure is presented. Appropriate interpretations of results and program output are illustrated. Some conclusions regarding the demonstration data within a juvenile justice prevention context are also discussed.
Files	Filename       Size       Approximate Download Time (Hours:Minutes:Seconds)     28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access    Thesis.pdf 1.36 Mb 00:06:16 00:03:13 00:02:49 00:01:24 00:00:07