Checking Stats of the Year 2019

What is your favourite statistic of the year and decade?

The Royal Statistical Society runs Statistic of the Year, highlighting prominent statistics in public debate. Since it is 2019, Statistics of the Decade was also discussed.

(Image: RSS)

As a Statistical Ambassador, I was asked to help check the submissions and their wording. In this article, I give my ratings and reasoning for each statistic I was asked to look at.

What was your stat of the year? (Video: YouTube)

Nomination: Between 2010 and 2018, an area equivalent to 7,226,217 football pitches was deforested in the Amazon Rain-forest.
Rating: Needs clarification.
Reasoning: Not all football pitches are the same size. Football pitches must be between 90m and 120m long, and between 45m and 90m wide.

International football pitches have a narrower range, between 100m and 110m in height, and between 64m and 75m wide. 10 of the 20 current FA Premier League teams have a pitch sized 105m by 68m, which meets international standards.

The official INPE estimates for Amazonian deforestation come from the PRODES project:

The PRODES estimates should be used, rather than the ‘flash’ DETER estimates. (Source: INPE)

The claim could be clarified about the months — as the annual study period runs from August to July. Additionally, it is false precision to say there were some exact number of football pitches.

The accumulated deforestation from August 2010 to July 2019 was an estimated 60,237 square kilometres. The standard football pitch size being used was 105m by 68m, or 0.00714 square kilometres.

Consequently, the claim could be clarified to:

From August 2010 to July 2019, the estimated accumulated deforestation of the Amazon rain-forest was around 8.4m football pitches.

Nomination: The celibacy rate among young American men aged 18–29 is 23%. This is surprisingly high when compared to the 50–59 age group, whose celibacy rate is only 13%.
Rating: Partially true.
Reasoning: The stated suvey estimate is for young people, aged 18–30 (23%). In the sample, 28% of US men aged 18–30 reported having no sex in the past year.

Also, 18% of young women have not had sex in the past year. (Image: Washington Post)

This is a survey estimate from the US General Social Survey. The question was:

About how often did you have sex during the last 12 months?

The General Social Survey is a random probability survey of US adults (aged 18 or over) conducted through face-to-face interviews.

Nomination: 58% — the proportion of those in poverty in working households.
Rating: Needs clarification.
Reasoning: This is based on analysis of the Living Costs and Food survey, by the Institute for Fiscal Studies. According to the Living Costs and Food Survey in 2017/18, 58% was the estimated proportion of households in relative income poverty that are working.

This proportion is very similar to an equivalent measure from the Households Below Average Income report (57%).

Nomination: 72.6 years — the average life expectancy around the world.
Rating: Needs clarification.
Reasoning: The figure is for life expectancy at birth. After 1950, the statistics come from the United Nations Population Division. The UN Population Division describes this measure as:

The average number of years of life expected by a hypothetical cohort of individuals who would be subject during all their lives to the mortality rates of a given period. It is expressed as years.

The increase was shown by Our World in Data, which can be commonly expressed in extra life in weeks (increased per year).

World life expectancy keeps on increasing. (Image: Our World in Data)

Nomination: Productivity, which grew around 2% a year before the financial crisis, has averaged just 0.3% annually for the last 10 years.
Rating: Needs clarification.
Reasoning: This claim appeared in a Bloomberg article. This is estimated by the Office for National Statistics. The measure that Bloomberg are referring to is output per hour worked.

There has been a sharp reduction in productivity increases since 2008. (Image: ONS)

The annual mean average from 1997 to 2007 was 2.2%. From 2008 to 2018, that average was 0.3%.

Nomination: In a car accident, women are 71% more likely to be injured than men due to safety equipment designed solely with male crash test dummies.
Rating: Needs clarification.
Reasoning: This figure comes from a paper written by Bose, Segui-Gomez, and Crandell in the US:

Results from the multivariate regression analysis indicated that the odds of a belt-restrained female driver sustaining an MAIS 3+ and MAIS 2+ injury were 47% (95% CI = 27%, 70%) and 71% (95% CI = 44%, 102%) higher.

The Abbreviated Injury Scale (AIS) severity score is an ordinal scale of 1 to 6 (1 indicating a minor injury and 6 being maximal). Injury, in that claim, refers to moderate injuries — or those more severe — to drivers.

This figure of 71% is an estimate, where women could plausibly be 44% to 102% more likely to suffer moderate or more severe injuries than men.

The paper itself does refer to crash test dummies:

To address these concerns, vehicle safety engineers assess the risk of injury during a crash by using a family of anthropometric test devices (e.g., crash test dummies) designed to represent occupants of both sexes and varying anthropometries.

Nomination: 165 million: the number of Sports Utility Vehicles (SUVs) has risen nearly six-fold, or by 165 million, over the past decade.
Rating: Needs clarification.
Reasoning: The IEA article does not list a source, but states:

As a result, there are now over 200 million SUVs around the world, up from about 35 million in 2010, accounting for 60% of the increase in the global car fleet since 2010.

This needs clarification, as the 165m figure is an approximation.

Nomination: Since 1990, the under-five mortality rate has decreased by 58% globally, from an estimated rate of 93 deaths per 1,000 live births in 1990 to 39 deaths per 1,000 live births in 2018.
Rating: Partially true.
Reasoning: Yes, the estimated rates are what the World Health Organisation states. The WHO article correctly says 59% — rather than 58% — for the decrease, due to rounding. In the press release, the absolute reduction was used.

Nomination: The average sugar content of drinks subject to the ‘Soft Drinks Industry Levy’ decreased by 28.8% between 2015 and 2018.
Rating: Needs clarification.
Reasoning: The claim comes from the Public Health England report on sugar reduction, published in September 2019:

The average sugar content of drinks subject to the Soft Drinks Industry Levy (SDIL) decreased by 28.8% between 2015 and 2018 (measured in sales weighted average grams per 100ml).

This claim needs to have the measurement added, to clarify.

Nomination: 87.2% — the proportion of UK children getting the second dose of the MMR vaccination (well below the 95% world target).
Rating: Partially true.
Reasoning: The stated figure is for 2017/18, referring to children in England. In September 2019, the figures for 2018/19 were published.

England is well-below the 95% world target. (Source: Public Health England)

In England, the proportion of children receiving the second dose of the MMR vaccine by their fifth birthday was 86.4%. No region of England met the 95% world target.

Nomination: 73% — a female occupant is 73% more likely than her male counterpart to be seriously injured in a frontal car crash.
Rating: Needs clarification.
Reasoning: This is a similar claim to one above. This comes from a 2019 paper by researchers from the University of Virginia, which was written about in Science Daily.

Women car passengers wearing seat-belts were an estimated 73% more likely to be seriously injured in frontal car crashes than men. This relative risk is after controlling for collision severity, age, stature, body mass index, and vehicle model year.

Nomination: 19% — the global death rate from indoor and outdoor pollution has declined by 19% in the last decade.
Rating: True.
Reasoning: That is right — the decade refers to 2007 to 2017.

The fall is explained by reductions in deaths from indoor air pollution. (Image: Our World in Data)

From 2007 to 2017, the global age-standardised death rate from attributed air pollution reduced by 19% (from 78.5 to 63.8 per 100,000 people).

This blog looks at the use of statistics in Britain and beyond. It is written by RSS Statistical Ambassador and Chartered Statistician @anthonybmasters.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store