Fiction, future, and prediction

I post about statistics and data in medical research. Every post ends with a section “Just one more thing” to provide a concrete data example with code in the R programming language that the reader can try out and examine.

1901

Statistical computing

Linux

While cleaning out my basement, I found a 20-year-old IBM computer. First, I wanted to get rid of it because the computer has become too old and useless. Instead, I installed a lightweight Linux operating system, R, RStudio, and analyzed the Titanic dataset as a showcase. It worked extremely well. Linux can bring new life to old computer hardware.

True colors

p-values

Science is often regarded as a fact producing machinery. However, a large proportion of the scientific findings may be wrong. This can be easily demonstrated with colors.

I don’t sleep, I dream

Animal studies

repeated inspection of data

p-values

A 2018 study reported in the methods section that the number of mice was continuously increased until statistical significance was reached. It is very easy to show that such approaches are flawed and belong in the realm of dark statistics because they are more likely to produce a false positive result.

Fake plastic trees

AI

Big Data

biomarkers

p-values

univariable screening

Data are often overvalued, while statistics are undervalued. New tools and technologies may not revolutionize healthcare but could instead create confusion about the validity of data and evidence. More data is not always better, and an example of misleading statistics is provided at the end.