Median Watch

Eyes on statistics

Scientific fraud is rising, and automated systems won’t stop it. We need research detectives

Reposted from The Conversation. Fraud in science is alarmingly common. Sometimes researchers lie about results and invent data to win funding and prestige. Other times, researchers might pay to stage and publish entirely bogus studies to win an undeserved pay rise – fuelling a “paper mill” industry worth an estimated €1 billion a year. Some of this rubbish can be easily spotted by peer reviewers, but the peer review system has become badly stretched by ever-rising paper numbers.

Posted by Adrian Barnett Friday, June 23, 2023

What to do when applying for research grants is a waste of time for almost everybody

Reposted with permission from Campus Morning Mail. Researchers have a dark sense of humour when it comes to research funding. One of my favourite sneers was from the ecologist Terry McGlynn who said, “instead of writing this grant, I should walk the whole country and get a penny from each person. Same amount of money, but less hassle.” Applicants to last year’s early- and mid-career Medical Research Future Fund fellowships may be wishing that they had gone on a long walk rather sitting at their computers, with speculated success rates at under 5 per cent.

Posted by Adrian Barnett Monday, March 6, 2023

Success without substance

Reposted with permission from 360info. New Zealander Nigel Richards has won the French Scrabble championship twice. What’s more remarkable than double wins is that Nigel doesn’t speak French. He applied his prodigious brain to the task of memorising words from the French dictionary, bypassing the need for understanding. In 2022, The Lancet medical journal achieved a feat that has parallels with Nigel’s Scrabble win. It achieved the highest ‘impact factor’ of any scientific journal in history.

Posted by Adrian Barnett Tuesday, January 31, 2023

Australia does not want to share health data

I am a statistician. I rely on data for my career. Luckily data is everywhere, so I’m often spoilt for choice. One place where I no longer look for existing data is the health and medical system in Australia. This comes from multiple painful experiences of spending months on approval processes that end in failure. Ad nauseum examples Many other researchers have spoken about the difficulties of accessing health data for research in Australia.

Posted by Adrian Barnett Friday, October 7, 2022

Publication bias or research misconduct?

In my talk on bad statistics in medical research, I showed the infamous plot of Z-values created by Erik van Zwet. A version of the plot made with David Borg is shown below. The sample size is over 1.1 million Z-values. {width=450px} The two large spikes in Z-values are just below and above the statistically significant threshold of ± 1.96, corresponding to a p-value of less than 0.05. The plot looks like a Normal distribution that’s caved in.

Posted by Adrian Barnett Monday, September 19, 2022