Maybe I'm missing something, but could someone explain the utility/ definition of the 'site-adjusted' ratios of geometric means in Figure 1 of the Jones et al. paper? Thanks
Hi Charles,
My understanding is that they ran models with and without a variable that reflected the 6 MESA study sites. I'm not sure what the value-added would be (or how appropriate it would be to adjust for site) given that have used a mixed model with a random intercept for census tract. I was wondering if MESA recruitment methods may have differed by site, given that they state "MESA recruitment methods did not ensure the representativeness of the source population. MESA participants were enrolled at each study site with the intent of having specific distributions across strata defined by race/ethnicity, gender, and age group, and not by random sample; because of this sampling strategy, MESA participants and their neighborhoods might not be representative of the race/ethnicity or spatial distribution of the populations at each site"? But unfortunately, they do not provide much more information about sampling in their methods.
My understanding is that they ran models with and without a variable that reflected the 6 MESA study sites. I'm not sure what the value-added would be (or how appropriate it would be to adjust for site) given that have used a mixed model with a random intercept for census tract. I was wondering if MESA recruitment methods may have differed by site, given that they state "MESA recruitment methods did not ensure the representativeness of the source population. MESA participants were enrolled at each study site with the intent of having specific distributions across strata defined by race/ethnicity, gender, and age group, and not by random sample; because of this sampling strategy, MESA participants and their neighborhoods might not be representative of the race/ethnicity or spatial distribution of the populations at each site"? But unfortunately, they do not provide much more information about sampling in their methods.
Thanks Leah! This is a great description. Agreed--re the level of detail on sampling. I was also surprised that they were unable to recruit people from some of the racial and ethnic groups in some of the locations. I'm curious how this may have affected the results and whether they used weighting to try to account for it. Maybe they mentioned it and I missed it.