• Report

2004 National Survey on Drug Use and Health - Summary report of generalized exponential model (GEM) calibration adjusted variance estimation (GEMRATIO).

Citation

Chen, P., Singh, A., & Folsom, R. (2005). 2004 National Survey on Drug Use and Health - Summary report of generalized exponential model (GEM) calibration adjusted variance estimation (GEMRATIO). (Prepared for Office of Applied Studies, Substance Abuse and Mental Health Services Administration, Rockville, MD). Research Triangle Park, NC: RTI International.

Abstract

RTI International started developing the generalized exponential model (GEM) calibration adjusted variance estimation (GEMRATIO) procedure in September 2002 with funding provided by the Substance Abuse and Mental Health Services Administration (SAMHSA), Office of Applied Studies (OAS). The GEMRATIO procedure in SUDAAN® was developed during 2002 and 2003. A brief report on the GEMRATIO study was sent to SAMHSA on June 29, 2004. On December 2, 2004, a report of a feasibility test to implement the procedure in the 2004 National Survey on Drug Use and Health (NSDUH) was submitted to SAMHSA. On December 23, 2004, SAMHSA decided that GEMRATIO would not be used for 2004 NSDUH analyses. This report has been prepared per SAMHSA's request to summarize the research work at RTI on the GEMRATIO procedure. SAMHSA would like to wait on the implementation of GEMRATIO until the component of variance due to imputation is examined.