Related Experiment Video
Updated: Aug 4, 2026

Using a Chemical Biopsy for Graft Quality Assessment
Published on: June 17, 2020
Pooled Bayesian meta-analysis of two Polish studies on radiation-induced cancers
1PGE EJ 1 Sp. z o.o., ul. Mysia 2, Warszawa 00-496, Poland krzysztof.fornalski@gmail.com.
Abstract:
The robust Bayesian regression method was applied to perform meta-analysis of two independent studies on influence of low ionising radiation doses on the occurrence of fatal cancers. The re-analysed data come from occupational exposure analysis of nuclear workers in Świerk (Poland) and from ecological study of cancer risk from natural background radiation in Poland. Such two different types of data were analysed, and three popular models were tested: constant, linear and quadratic dose-response dependencies. The Bayesian model selection algorithm was used for all models. The Bayesian statistics clearly indicates that the popular linear no-threshold (LNT) assumption is not valid for presented cancer risks in the range of low doses of ionising radiation. The subject of LNT hypothesis use in radiation risk prediction and assessment is also discussed.
Related Concept Videos
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Comparing the Survival Analysis of Two or More Groups
Cancer Survival Analysis
