Statistics: if you torture the data enough, they will confess. clemsonunivlibrary/ Flickr

One reason so many scientific studies may be wrong

P hacking is manipulating data and research methods to achieve statistical signifiance. And it could be why so many research papers are false.
A p value of .05 has been the default ‘significance’ threshold for nearly 90 years … but is that standard too weak? Martin_Heigan

The problem with p values: how significant are they, really?

For researchers there’s a lot that turns on the p value, the number used to determine whether a result is statistically significant. The current consensus is that if p is less than .05, a study has reached…
A small experiment won’t identify even a large effect as significant while a big experiment is likely to see even a worthless effect as statistically significant. 8 Eyes Photography Flickr

Mind your confidence interval: how statistics skew research results

“Most patients using the new analgesia reported significantly reduced pain.” Such research findings sound exciting because the word significant suggests important and large. But researchers often use the…

Contact Geoff for

  • General
  • Media request
  • Speaking request
  • Consulting / Advising
  • Research collaboration
  • Research supervision