Measuring and Modeling Health Disparities: Methodological Challenges and Recommendations

2.50
Hdl Handle:
http://hdl.handle.net/10755/160898
Type:
Presentation
Title:
Measuring and Modeling Health Disparities: Methodological Challenges and Recommendations
Abstract:
Measuring and Modeling Health Disparities: Methodological Challenges and Recommendations
Conference Sponsor:Midwest Nursing Research Society
Conference Year:2006
Author:Templin, Thomas, PhD
P.I. Institution Name:Wayne State University
Title:Associate Professor
Contact Address:Center for Health Research, 5557 Cass Ave., Detroit, MI, 48202, USA
Contact Telephone:313-577-7992
The purpose of this didactic presentation is to highlight the methodological challenges in health disparities research and current recommendations from a wide range of literature. Recommendations from the methodological literature in nursing, epidemiology, psychology, medicine, and econometrics were examined. Four areas emerged: (1) Use of the race/ethnicity variable in causal models; (2) Evaluation of psychometric validity; (3) Methods to identify and control sources of confounding in causal models and (4) CDC guidelines on the measurement of health disparities. Recommendations include the following: The specific causal variables that race/ethnicity might be considered a proxy for should be identified and measured. The nominally coded race/ethnicity variable is often correlated with but not causally connected to the primary explanatory variables. Measurement validity should be established by qualitative and quantitative methods and homogeneous subgroups should be used when testing invariance to avoid specific factor bias. In addition to classic reliability analysis, analysis of differential item functioning should be carried out prior to comparing groups. Structural models need to take mediation, effect modification, and potential conditioning by secondary outcomes variables into account. And finally, more attention should be paid to sampling designs which allow representation of a broader range of socio-demographic variables to reduce the high covariance among risk, protective and confounding variables. Conclusion. Causal interpretation of observational health disparity data should be informed by current thinking in the areas outlined. [Poster Presentation]
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Midwest Nursing Research Society

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleMeasuring and Modeling Health Disparities: Methodological Challenges and Recommendationsen_GB
dc.identifier.urihttp://hdl.handle.net/10755/160898-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Measuring and Modeling Health Disparities: Methodological Challenges and Recommendations</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Midwest Nursing Research Society</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2006</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Templin, Thomas, PhD</td></tr><tr class="item-institute"><td class="label">P.I. Institution Name:</td><td class="value">Wayne State University</td></tr><tr class="item-author-title"><td class="label">Title:</td><td class="value">Associate Professor</td></tr><tr class="item-address"><td class="label">Contact Address:</td><td class="value">Center for Health Research, 5557 Cass Ave., Detroit, MI, 48202, USA</td></tr><tr class="item-phone"><td class="label">Contact Telephone:</td><td class="value">313-577-7992</td></tr><tr class="item-email"><td class="label">Email:</td><td class="value">ac0410@wayne.edu</td></tr><tr><td colspan="2" class="item-abstract">The purpose of this didactic presentation is to highlight the methodological challenges in health disparities research and current recommendations from a wide range of literature. Recommendations from the methodological literature in nursing, epidemiology, psychology, medicine, and econometrics were examined. Four areas emerged: (1) Use of the race/ethnicity variable in causal models; (2) Evaluation of psychometric validity; (3) Methods to identify and control sources of confounding in causal models and (4) CDC guidelines on the measurement of health disparities. Recommendations include the following: The specific causal variables that race/ethnicity might be considered a proxy for should be identified and measured. The nominally coded race/ethnicity variable is often correlated with but not causally connected to the primary explanatory variables. Measurement validity should be established by qualitative and quantitative methods and homogeneous subgroups should be used when testing invariance to avoid specific factor bias. In addition to classic reliability analysis, analysis of differential item functioning should be carried out prior to comparing groups. Structural models need to take mediation, effect modification, and potential conditioning by secondary outcomes variables into account. And finally, more attention should be paid to sampling designs which allow representation of a broader range of socio-demographic variables to reduce the high covariance among risk, protective and confounding variables. Conclusion. Causal interpretation of observational health disparity data should be informed by current thinking in the areas outlined. [Poster Presentation]</td></tr></table>en_GB
dc.date.available2011-10-26T23:12:33Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T23:12:33Z-
dc.description.sponsorshipMidwest Nursing Research Societyen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.