Abstract

Studies have demonstrated that exposure to moderate-to-high levels of ionizing radiations can cause most forms of cancer, leukemia, cardiovascular diseases, stroke, etc., especially at young ages. Hence, study of exposure to radiation has been the subject of intense epidemiological investigation. For experimentation purpose, we have used Hiroshima and Nagasaki atomic bomb survivor data, 1950-2003, Br Med J. 2010, 340:193. We have found this count cohort data to be over dispersed, which has led us to experiment negative binomial regression modelling on it, as it is over-dispersed in itself. We have estimated risk of cardiovascular data w.r.t. dose-category of radiation. As per our model, we have found that doses above 1.25 Gy are associated with an elevated risk of cardiovascular diseases, but the degree of risk at lower doses is unclear.

Keywords: AIC (Akaike Information Criterion); Cohort data; Epidemiology; Over-dispersion; Regression; Relative risk