Back to Annual Meeting Page		American Public Health Association 133rd Annual Meeting & Exposition December 10-14, 2005 Philadelphia, PA

Abstract #108579

Stuart A. Gansky, DrPH, Center to Address Disparites in Children's Oral Health, University of California, San Francisco, 3333 California St, San Francisco, CA 94143-1361, 415-502-8094, sgansky@itsa.ucsf.edu

Many research studies involve ordinally scaled strata for adjustment. For example, in health disparities research, adjusting for socioeconomic status is necessary before comparing disease status across racial/ethnic groups. A minimal assumption, nonparametric, randomization-based extended Mantel-Haenszel (EMH) test is frequently used to analyze such studies. Thus, a stratum scale-adjusted EMH (SAEMH) test was developed with an extra set of scores corresponding to the ordinally scaled strata using scores such as standardized midranks. Monte Carlo simulations with and without actual scale-response effects and 1000 replicates estimated empirical size and power. Results showed improved power for the SAEMH versus the EMH for an actual scale-response and not much difference in power when an actual scale-response did not exist. Support: US DHHS/NIH/NIDCR, NCMHD U54 DE 14251.

Learning Objectives:

• Understand the use of scores for traditional minimal assumption Mantel-Haenszel tests and their extensions
• Understand ordinally scaled potential confounding variables in Health Disparities
• Learn the benefits and limitations of a stratum scale-adjusted Mantel-Haenszel Test to assess Health Disparities

Keywords: Biostatistics, Health Disparities

Presenting author's disclosure statement:

I wish to disclose that I have NO financial interests or other relationship with the manufactures of commercial products, suppliers of commercial services or commercial supporters.