Statistical Consulting Section

Thanks for the insights everyone! A lot of good ideas to consider. Perhaps a less restrictive approach--additive model, gamlss, etc---is the way to go. For good or for ill (probably the latter) most of the social-determinant-of-health predictors are ... More

This is great Nora, thanks! I will definitely dig into that. ------------------------------ Christopher Ryan Agency Statistical Consulting, LLC ------------------------------ More

Hi Christopher, The recent (2024) 2nd edition of Stroup, Ptukhina and Garai: "Generalized Linear Mixed Models: Modern Concepts, Methods and Applications" presents state-of-the-art discussions on important issues associated with modeling of rates and ... More

We could find a distribution to fit. If nothing else, R's logspline package has a very effective semiparametric approach. But why do you want to fit the distribution? What is your research question? It sounds like relating A1c to other covariates ... More

Christopher, As an engineer, I am not familiar with any prior distributional modeling of A1c data or if there are biologically preferred variability distributions for parametric interpretation. However, the Reliability field of engineering ... More

Added to the modest but growing list of humor that involves statistics Christopher Walken (without cowbell) and the census enumerator (from 2000) https://www.nbc.com/saturday-night-live/video/the-census/2749920 in case anyone is not familiar ... More

If this is a medical research project and not a statistics research project, I would recommend against transforming A1c. It is pretty much always presented with means and standard deviations in its natural units, and clinically meaningful changes are ... More

I don't know the answer. However, NHANES does collect HBA1C and seems to have some suggestions for the statistical analysis In advance I realize you're not using NHANES link from CDC here https://wwwn.cdc.gov/Nchs/Nhanes/2015-2016/GHB_I.htm ... More

Hi Christopher, I wonder if you need the Beta here. It can be difficult to work with in modeling, e.g., because observed values of exactly 0 and 1 aren't allowed (though not an issue in your case unless you plan to rescale the data to match the Beta's ... More

I'm helping a colleague and his team of residents and medical students with a cross-sectional chart review study of hemoglobin A1c levels in patients with type 2 diabetes, and how (if at all) they relate to a variety of "social determinants of health": ... More