Statistical power of epidemiological studies of low dose levels of ionizing radiation and cancer
Date
2020-05-04
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
ORCID
Type
Thesis
Degree Level
Masters
Abstract
The purpose of this research is to inspect the statistical power of studies that investigate
the effects of low dose ionizing radiation on the incidence of/mortality from cancer. I use
a procedure proposed in a similar study to handle a problem regarding the incidence of
childhood leukemia from background ionizing radiation. I study this procedure critically
and make some adjustments to make its performance better. I also propose some substitute
methods to the methods proposed in the aforementioned reference in order to calculate
the power. In addition, I propose other methods not used in the study mentioned above.
I evaluate the efficiency of my proposed approaches using simulated data. The improved
method can be applied to the National Dose Registry of Canada (NDR) to produce the
power curves. The outcomes then can be used to propose the most suitable study design.
Some of the previous epidemiological studies based on NDR can also be evaluated in terms
of power.
Description
Keywords
Statistical power, Ionizing radiation, Score test statistic
Citation
Degree
Master of Science (M.Sc.)
Department
School of Public Health
Program
Biostatistics