Extended Data Table 9 Logistic regression models used to estimate probabilities for inverse probability weighting: selection into HUNT3 based on HUNT4 70+ (Model 1) and donation of blood samples in HUNT4 70+ (Model 2)

From: Prevalence of Alzheimer’s disease pathology in the community

  1. CU = cognitively unimpaired; MCI = mild cognitive impairment; Std. Err. = standard error; Yr = years; APOE = apolipoprotein E. Model 1 estimates the probability of being selected into the HUNT3 nested study based on cognitive status at HUNT4 70+; Model 2 estimates the probability of donating a blood sample at HUNT4 70+. Estimates are presented on the logit scale; appropriate transformations were applied to obtain final probabilities for weight calculation.
Back to article page