Calibration and Seasonal Adjustment for Matched Case-Control Studies of Vitamin D and Cancer

• Activity Number: 666 - Prediction and Calibration
• Type: Contributed
• Date/Time: Thursday, August 3, 2017 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Mitchell Gail * and Jincao Wu and Molin Wang and Shiaw-Shyuan Yaun and Nancy R. Cook and A. Heather Eliassen and Marjorie L McCullough and Kai Yu and Anne Zeleniuch-Jacquotte and Stephanie A. Smith-Warner and Regina G. Ziegler and Raymond Carroll
• Companies: National Cancer Institute, NIH, HHS and Food and Drug Administration and Harvard T. H. Chan School of Public Health and Channing Division of Network Medicine and Harvard T. H. Chan School of Public Health and Harvard T. H. Chan School of Public Health and Harvard T. H. Chan School of Public Health and American Cancer Society and National Cancer Institute and New York University School of Medicine and Harvard T. H. Chan School of Public Health and National Cancer Institute and Texas A&M University
• Keywords: calibration ; seasonal adjustment ; matched case-control study ; molecular epidemiology ; biomarker ; measurement error

Abstract

Vitamin D measurements are influenced by seasonal variation and specific assay used. Motivated by multicenter studies of vitamin D with cancer, we give an analytic framework for matched case-control data that accounts for seasonal variation and calibrates to a reference assay. Key findings include: (1) Failure to adjust for season and calibration increased variance, bias and mean square error. (2) Analysis of continuous vitamin D requires a variance adjustment for variation in the calibration estimate, but log odds estimates do not depend on a reference date for seasonal adjustment. (3) For categorical vitamin D risk models, procedures based on categorizing the seasonally adjusted and calibrated vitamin D levels have near nominal operating characteristics. However, estimates of category-specific log odds ratios depend on the reference date for seasonal adjustment. Thus public health recommendations based on categories of vitamin D should also define the time of year to which they refer. This work is informing the analyses of the multicenter Vitamin D Pooling Project for Breast and Colorectal Cancer.