# Articles on Statistics

## The genius at Guinness and his statistical legacy

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.

## Maths is revolutionising the study of history – here’s how

The internet has not only changed the kinds of answers historical study can provide, but also what questions can be asked.

## Why economists are calling for the RPI inflation measure to be scrapped

The Retail Prices Index (RPI) is responsible for rising rail fares and student loan repayments.

## How AI could help football managers spot weak links in their teams

A new approach to gathering data from football matches which uses cybernetics and AI could help coaches spot weak links in their teams.

## Are autonomous cars really safer than human drivers?

Comparing crash rates between humans and self-driving cars requires more data than anyone currently collects. And some of it will be quite hard to figure out.

## What the stats say: is Steve Smith the second-best Australian cricket batsman ever?

Australian cricket captain Steve Smith's play during the recent Ashes saw him hailed as one of the greatest Australian players. So what do the numbers say?

## Bad data collection means we don’t know how much the middle class is being squeezed by the wealthy

The squeeze on wealth in the middle class by those at the top is a long established trend in international inequality data. But the ABS doesn't provide this information.

## How the same-sex marriage survey got us talking about – and trusting – data

The same-sex marriage postal survey gave Australians a chance to create data for social change. And that's rare.

## What the numbers say (and don’t say) in the same-sex marriage survey

Not everyone who could vote did vote in the voluntary postal vote on same-sex marriage. So what can we draw from the result if only four out of five eligible Australians took part?

## Science’s credibility crisis: why it will get worse before it can get better

We are observing two new phenomena. On one hand doubt is shed on the quality of entire scientific fields or sub-fields. On the other this doubt is played out in the open, in the media and blogosphere.

## Why Puerto Rico ‘doesn’t count’ to the US government

Although Puerto Ricans are American citizens, what happens on the island tends to stay there, at least in terms of economic data.

## The psychology of the clutch athlete

What makes someone more likely to succeed when the lights shine brightest?

## A statistical fix for the replication crisis in science

Scientists have a big problem: Many psychological studies don't hold up to scrutiny. Is it time to redefine statistical significance?

## Our calculator will guess how many healthy years of life you have left

How many healthy years of life do you have ahead before you become unhealthy – and then die? One model tries to find the answer.

## Are catastrophic disasters striking more often?

Saturated media coverage of hurricanes like Harvey and Irma can make it seem like disasters happen all the time. Is the frequency of billion-dollar disasters really rising?

## What the physics of bubbles can tell us about language

Humans behave like atoms when viewed from a distance.

## Women now have clearer statistics on whether IVF is likely to work

Women will now be better informed when it comes to deciding whether it's worth undergoing another round of IVF.

## In a victory against spin, ministers lose pre-release access to statistics

No democratic government should be able to manipulate the public by getting a sneak peek at the data.

## Don’t blame it on algorithms: what they really are and how they can fuel progress in the life sciences

Today algorithms are ubiquitous, yet often misunderstood. Rather than mysterious entities, they're closer to recipes, and the quality of the output depends on the input – in their case, data.

## Cracking big data with statistical physics

Methods stemming from decades of research on disordered materials are used to describe algorithmic phase transitions, and to design new algorithms in machine-learning problems.

More Jobs