Presentation: Assessing the Impact of Unmeasured Confounding in the Life Span Study of Atomic Bomb Survivors
Speaker: Benjamin French, PhD, Senior Scientist, Department of Statistics, Radiation Effects Research Foundation
Abstract: The Life Span Study of atomic bomb survivors includes residents of Hiroshima and Nagasaki, Japan, who were within 10 km of the hypocenter at the time of the bombings in 1945, and a matched sample of Hiroshima and Nagasaki residents who were not in either city at the time of the bombings. Radiation risk estimates from the Life Span Study are used to inform policies for radiological protection in occupational, medical, and public health settings, as well as for atomic bomb survivors’ welfare. Differences in unmeasured factors across expsoure levels could confound the association between radiation dose and outcome risk. We therefore assessed the sensitivity of radiation risk estimates for incident solid cancer to the choice of the reference group, considering zero-dose survivors at different ground distances from the hypocenter and not-in-city residents. Observed risk differences motivated development of new methods to conduct sensitivity analyses for unmeasured confounding with multiple correlated comparisons, while controlling for multiplicity error. Our approach—based on evidence factors—allows for a comprehensive examination of the potential impact of unmeasured confounding, while retaining statistical power. Ongoing research seeks to extend this approach to estimation of dose-response curves.