Have you unintentionally misreported your gender pay gap?

As many as one in six organisations have reported their gender pay gap incorrectly, according to independent data analysis. Organisations most commonly made one of three errors, often not intentionally but because of confusion about what data has to be entered. How accurate are your calculations?

An independent statistician reported findings from research in PersonnelToday, following an analysis of reports. Below is an extract from this report, highlighting the three most common errors. There is also a link to the actual report.

1. Mathematical errors

Some organistions said their gender pay gap was greater than 100%, which is impossible since it would mean women are actually paying their employer to work there, or they are paid nothing, which obviously cannot happen.

You can see examples of this error from Shrewsbury Academies Trust and ‘Partnering Health’ by following the links to the article below 

2. Income quartiles entered the wrong way around

Quartiles are where an organisation is split into four equally sized chunks of employees based on their hourly earnings (including bonuses) and then the gender split is recorded.

Quartiles can offer the most valuable insight into gender pay gap data – and they also provide a useful error check. One organisation, for example, recorded a median gender pay gap of +9%, which is similar to the national median. Yet, based on their quartile data, it is possible that they should have recorded -9%, where the median woman is paid more than the median man.

An example and a chart are provided in the article, which states ‘Suppose that 400 people work for the council. Using the quartile percentages from the chart, that means there are 293 women and 107 men working for the council. To find the median woman, the 293 women have to “stand in a line” in order of their hourly earnings. The 147th woman becomes the median, as does the 54th man.

Based on these calculations, the median woman would sit in the upper middle income quartile, whereas the median man would sit in the lower income quartile. Therefore the median man would be earning less than the median woman, and the reported gender pay gap data should be negative (as in, women earn more).’

Again, you can see examples of this error by following the links to the article below 

3. Claim of no pay gap conflicts with the male quartile gap

It is easy to see that if an organisation is reporting a positive median (not mean) gender pay gap, then this must imply that the sum of the percentage of men in the upper and upper middle quartiles should be greater than the sum of the male percentages in the other two quartiles.

The below calculations provide a quick sanity check to figure out if there is an error.

Calculate the male quartile gap as the sum of the male percentages in the upper and upper middle income quartile. Then subtract the sum of the male percentages in the lower and lower middle income quartiles.

If the median gender pay gap is positive then the male quartile gap must be positive. If the median gender pay gap is negative, then the male quartile gap should also be negative.

If this check is violated then an error has been made. For example, one organisation claims a negative median gender pay gap of -13%, which means the inequality 75% + 47% – 45% – 56% < 0% should be true, but this clearly isn’t the case.

The research found that 937 organisations reported a median gender pay gap of zero. However, this can only be correct if the male quartile gap is virtually zero. Of these, 374 organisations have male quartile gaps between -5% and +5% so they could be correct but their data should still be checked. That still leaves 564 organisations that must have made a mistake.

You can obtain clarification of the above text and see further information and examples by taking a look at the report which can be accessed here