Methodological problems in epidemiological data: the case of correlation between radon level and lung cancer
by Joanna Reszczyńska; Maciej Pylak; Krzysztof W. Fornalski; S.J. Mortazavi; L. Dobrzyński
International Journal of Low Radiation (IJLR), Vol. 11, No. 3/4, 2020

Abstract: This paper focuses on the relationship between radon concentration and lung cancer morbidity from the methodological point of view. Geographically aggregated data on cancer risk factors, collected for 3142 US counties and county-equivalents are discussed. Apart from the Least-Squares and Bayesian linear regression analysis, for the first time the Maximum Entropy Method (MEM) is used to investigate this type of correlation, where major confounding factors under considerations are altitude and ultraviolet (type B) radiation. First two methods of analysis show statistically significant decrease in the group with the high smoking prevalence. This trend did not depend on the sex of the subjects or their prevalence of smoking. The use of MEM provides a much richer picture of a clear trend of decreasing morbidity of lung cancer with increasing radon concentration level. Last but not least, it is shown that the data binning has to be made carefully as otherwise the conclusions based on the data can be dubious.

Online publication date: Wed, 10-Mar-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Low Radiation (IJLR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com