Group items tagged

Excellent analysis from the FT (you'll need to login to view via the link) that uses knowledge of the Mean and Median to show that some companies have reported incorrect (fabricated?) pay-gap information! One in 20 UK companies that have submitted gender pay gap data to the government have reported numbers that are statistically improbable and therefore almost certainly inaccurate, a Financial Times analysis has found. Sixteen companies, each with more than 250 employees, reported that they paid their male and female staff exactly the same, that is they had a zero average gender pay gap measured by both the mean and median. Experts on pay said that it was highly anomalous for companies of that size to have median and mean pay gaps that were identical because the two statistics measure different things. The mean gap measures the difference between the average male and female salary while the median gap is calculated using the midpoint salary for each gender.

In 1967, following riots in Detroit, Philip Meyer used survey research methods, powered by a computer, to show that college-educated people were just as likely to have rioted as high school drop outs. His story was one of the first examples of computer assisted reporting and precision journalism, in which journalists use social science methodologies to extract and tell stories. In recognition of his contribution to the area, each year's best computer-driven and precision stories are celebrated through the Philip Meyer Journalism Award. The Award's 2016 winners have just been announced, with the successful entries showcasing techniques derived from quantitative and qualitative methods, such as surveys using randomly-selected respondents, descriptive and inferential statistical analysis, social network analysis, content analysis, field experiments, and more.

Uses the example of health treatments to illustrate some of the problems with using the average

As students from privileged backgrounds flock to schools that were supposed to be the ultimate symbol of egalitarianism, experts fear they may be reinforcing class and cultural divisions

This is an example of imprecise communication - it's right to talk about percentage increase (rather than percentage point change) but it isn't clear what the baseline was which makes it a bit confusing (475,000/120*100 will give you the median price 3 months ago of 395833.33). Note the use of the median rather than the mean - remember why that's a sensible idea in this context! Home prices have risen by more than 20 per cent to a $475,000 median. The change in median price over the past year was up by 26.7 per cent. And compared to three years ago Cremorne prices have grown by almost 40 per cent. Look back five years and prices have increased by a mighty 70 per cent, the report revealed.

When talking about the gender pay gap people tend to talk about the median figure rather than the mean. The mean is calculated by adding up all of the wages of employees in a company and dividing that figure by the number of employees. This means the final figure can be skewed by a small number of highly paid individuals. The median is the number that falls in the middle of a range when everyone's wages are lined up from smallest to largest and is more representative when there is a lot of variation in pay.

Use of mean and median to analyse the paygap at The Guardian group. The gender pay gap at Guardian News & Media is 11.3% - calculated by mean hourly pay - the company has reported as part of the government's compulsory gender pay gap initiative.Across GNM, the median pay difference, which takes the mid-point when all wage rates are lined up from the biggest to smallest - which reduces the impact of one-off outliers - is wider, at 12.1%. The figure for non-editorial is 18.2%, and nearly 9% in editorial.

The histogram is one of my favorite basic chart types, because it lets you quickly see the shape and distribution of a dataset. However, a lot of people don't know what a histogram shows or how the chart works.

The reasons for the disparity in pay vary from company to company but the broader source of the gap can be seen in the distribution of high earners by gender. Of all the companies that have reported to date the top pay quartile, the highest paid 25% of employees, is male-dominated. Almost two-thirds of the top quartile is made up of men, while conversely 57% of the lowest-paid employees are women.

Some fantastic visualisations in this piece from the Guardian, including a scatterplot and some different kinds of histograms! Well worth exploring. "The figures reveal men are paid more than women in 7,795 out of 10,016 companies and public bodies in Britain, based on the median hourly pay. Across the companies and organisations that had filed by 8am on Thursday, eight out of 10 had a gender pay gap. While the figures do not reflect equal pay for equal work, they do raise questions about structural inequalities in the workforce and may hold the answer to closing the gap."

Really good video illustrating how (a) gathering data, and (b) understanding the shape of that data can give us insight onto real world issues, and help us to target approaches to tackling them "Britain has carried out one of the biggest data-gathering exercises on the gender pay gap, exposing large disparities between the average pay given to men and women in some of the country's best-known companies. We dispel some of the myths around the gap, and explain what it really means and why it matters"

Public sector employers with more than 250 staff are legally obliged to publish their gender pay gap by Friday, while private firms and charities have until Wednesday 4 April. About 7,000 of a estimated total of 9,000 organisations had filed results by Thursday.companies have filed mathematically impossible figures - at least 17 have reported a bonus gap of more than 100%. One company reported an hourly mean gender pay gap of 106.4%, implying that for every £100 earned by a man a woman would "pay" £6.40. A spokesperson at the company declined to comment.