Equalizing Variables Across Groups
Posted on December 5, 2011
Benjamin Lê Cook (bio) looks at ways to put the Institute of Medicine's definition of racial disparity into practice.
We're trying to operationalize this Institute of Medicine definition. And what they said was that disparity is all differences, except those due to clinical appropriateness and need and patient preferences. And then we go to a survey like the National Survey of Drug Use and Health. And there are a whole host of variables, and you have to kind of select those that you think relate to clinical appropriateness and need.
And so, for us, a shorthand way of saying that is, "Let's select all those that have to do with health status." If we're looking at drug treatment, we'll look at an individual's drug abuse and the National Survey of Drug Use and Health has plenty of variables that talk about an individual's severity of their dependence and their abuse. Those are clearly clinical appropriateness and need variables. And then there are others that are very closely aligned with health status.
So for substance abuse, for example, age is a very large predictor of whether an individual will be using substances. And very related to whether drug treatment is clinically appropriate, also. So we'll grab all of those variables that we think are clinically... are variables that touch upon health status or clinical appropriateness and need. And we'll think of those as the ones that we want to equalize cross the groups.
Excerpted from an interview with the researcher conducted at the 2011 NHSN Conference held in Miami, FL.
Please note that the feedback is viewed only by 4researchers staff and is not intended for communication with individual contributors.
Use the form below to submit feedback about this article. If you would like a response, please be sure to include your e-mail address.