Page 34 - Contributed Paper Session (CPS) - Volume 1

CPS694 Ordak Michal

A critical image of statistical analyses in medicine
between 2006 and 2018
Ordak Michal
Department of Pharmacodynamics, Centre for Preclinical Research and Technology (CePT),
Medical University of Warsaw, Poland

Abstract
Statistics play an extremely important role in medicine. Over a period of 13
years, i.e. between 2006 and 2018, I observed a negative trend in medical
statistics. At that time, I examined a group of 14,000 people working in the
medical environment, including doctors and researchers. The paper presents
the basic mistakes made by the medical community in the performance of
statistical analysis. For this purpose, I analyzed additional 30 publications from
50 medical journals (n = 1500). During the last thirteen years, i.e. between 2006
and 2018, I carried out 25,300 statistical consultations in a group of students
of various medical majors. Only 40% of the articles analyzed contained correct
statistical analyses. The most common errors I have noticed include: no
description or the use of wrong statistical tests (assumptions of parametric
equivalents are not met) and an incorrect record of results obtained. During
the last thirteen years, I carried out 25,300 statistical consultations in a group
of students of various medical majors. Almost 95% of respondents said that
their insufficient knowledge of statistical analysis results from four factors.
What education path should be chosen to increase the quality of statistical
analysis performed by the future medical community? This paper answers
these questions.

Keywords
Biostatistics; Medical statistics; Statistics education

1. Introduction
In this age of modern technologies and development, medicine is one of
the most dynamic areas of life. Statistics play an extremely important role in
medicine. They are a source of knowledge about people and their lives. They
should be a ‘signpost’ for all medical employees. The thousands of statistical
analyses and reviews that I carried out between 2006 and 2018 have inspired
me to write this abstract. Nowadays, due to many factors, people performing
statistical analyses in medicine do not really realise how many significant errors
they make. This is connected with the pressure to publish results in high-ranked
journals. Consequently, many medical researchers break statistical rules in
order to obtain statistically significant results. I would, therefore, like to provide

23 | I S I W S C 2 0 1 9