A new statistical test lets researchers search for similarities between groups. Could this help keep new important findings out of the file drawer?
Police practices like stop and frisk are often criticized as racial profiling. But it can be tricky to figure out from the data which officers are the worst offenders.
What do stats really mean in the real world? Here's an example from leukaemia research to help you identify if a result really is important.
Shrewd media consumers think about these three statistical pitfalls that can be the difference between a world-changing announcement and misleading hype.
McDonald's Canada has brought back its popular Monopoly game. A statistician explains the odds of winning the top prizes and how that compares to the odds we confront in everyday life.
A new machine-learning algorithm does more with less.
The odds favor a big year for Democrats, but the extent of their gains is still in doubt.
Lotteries purportedly generate money to support public education. Jackpots are getting bigger and bigger – but states don't seem to be spending any more on education.
When political polls are aggregated together, that can make the results misleading.
What's really the most dangerous American city? The way crimes are currently counted in the US can easily confuse and mislead.
Undergraduate statistics degrees have tripled in the past decade. Is 'statistician' really the sexy new job?
Galaxy images and patient records can be equally confusing. Now a team of astrophysicists have realised their methods could help medical professionals.
The best team to lift the trophy was Brazil's star-studded 1970 team.
A survey shows that most Puerto Ricans didn't highly rate the official information coming out of the island. With the Institute of Statistics in trouble, the situation is likely not to improve.
Australia has won the soccer World Cup three times, in simulation games only. So what are the challenges to predicting the winner?
The government said 64, journalists said 4,645. What went wrong?
We are often presented with surveys that claim to show how we all think on a certain subject. But how many people do you need to ask for that finding to have have any convincing meaning?
Statistics are political – so we should question the recent drop in government estimates of British citizens living in the EU.
If journal editors fail to retract or properly flag data revealed as inaccurate, they leave open the possibility that it'll be cited for years to come.
A statistical method widely used today by scientists and others is all thanks to a statistician at a Guinness brewery whose work was published anonymously more than a century ago.