Modeling Hierarchical Structure of Complex Data from a Network of Drug Treatment Programs

• Activity Number: 259
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Carrie J. Tillotson*+ and Dongseok Choi and KIm Hoffman and Dennis McCarty
• Companies: Oregon Health & Science University and Oregon Health & Science University and Oregon Health & Science University and Oregon Health & Science University
• Keywords: multilevel models ; generalized mixed models ; drug treatment ; quality improvement ; retention in care ; wait time

Abstract

The Network for the Improvement of Addiction Treatment (NIATx) applies process improvement strategies to enhance the quality of care for the treatment of alcohol and drug disorders. Data from 15 of the agencies participating in the NIATx, followed over 15 months, were examined to assess the impact of days from contact to first treatment on completion of four sessions of care. Preliminary analyses show evidence of time-varying association in some agencies but not others. Several models have been fitted to model the hierarchical structure of agencies and months within agencies, including logistic regression, generalized linear mixed models and multilevel models. Results for each model fit are compared graphically and by model fit statistics. Implications of choosing various model fits are discussed.