Handling missing data in an FFQ: multiple imputation and nutrient intake estimates.

Mari IchikawaAkihiro HosonoYuya TamaiMiki WatanabeKiyoshi ShibataShoko TsujimuraKyoko OkaHitomi FujitaNaoko OkamotoMayumi KamiyaFumi KondoRyozo WakabayashiTaiji NoguchiTatsuya IsomuraNahomi ImaedaChiho GotoTamaki YamadaSadao Suzuki

Published in: Public health nutrition (2019)

Our results indicate that missing values due to zero intake, namely missing not at random, in FFQ can be predicted reasonably well from observed data. Multiple imputation performed better than zero imputation for most nutrients and may be applied to FFQ data when missing is low.

Keyphrases

electronic health record
big data
heavy metals
artificial intelligence
weight loss