Blog by Deniz Gursul, Campaigns and Policy Manager at the RSS
The theme for the RSS William Guy Lectureship 2024-25 is ‘statistics in plain sight’. But what does that actually mean?
Statistics in plain sight
Consider a typical day – the alarm goes off and you set out to get ready for work.
First things first: breakfast. As you pop your bread in the toaster, you lament the recent increases in price of your breakfast ingredients. Inflation and the cost-of-living crisis have been much discussed over recent months. But while the headline inflation figure is reported widely on the news, less discussed is how this figure is actually calculated. Because this figure is composed of prices of a range of different goods and services (including your loaf of bread) rather than being a number that can be measured directly, it’s actually a statistic – as we have discussed in a blog on this topic previously.
Next up: time to get dressed. But first – what’s the weather forecast? How cold is it going to be? Is it going to rain today? There are a whole host of statistics involved in trying to predict whether you should pack your brolly or gloves. Weather 'forecasts' are inherently statistical – they involve using current or past data to make predictions about future events. Data on what the weather is like now and how it has behaved in the past will inform the double drops or rays of sunshine predicted on your weather app.
As you opt for your jumper, you consider the statistics that led to this item making its way into your hands. These statistics range from sizing and design to market research and sales. They include the many measurements of bodies of all shapes and sizes to determine what a size ‘medium’ is, as well as the market research investigating the most sought-after trends, styles and colours to inform stocking decisions. Retailers will likely also analyse sales data across the country to consider whether people in certain areas are more likely to buy particular products or styles, and adjust their offer accordingly.
Time to check the commute. You open your navigation app, which will be using a range of statistics to tell you the most efficient way to get to work. Real-time traffic data on how busy roads, buses, trains, or tubes are, can be combined with data on past patterns to recommend the speediest route to the office. This can get detailed, with information down to which tube carriage will be most or least likely to feel like a game of ‘sardines’. On a broader level, data on what sort of transportation people usually take and at what time can be used to inform the train and bus schedules – with increased service at peak times throughout the day and less at others.
While brushing your teeth, you take a few moments to sneakily check your social media. You are amazed yet again by the targeted posts and ads you receive – how do they know your interests so well? Algorithms – a crucial building block of data science – are the answer. As you mindlessly scroll and search, a range of data is collected on what you are looking at. When it comes to showing you new content, this needs to be prioritised. What will keep you hooked for longest? An algorithm helps to do this: a set of rules to decide what you should be shown, according to factors such as your past preferences, the novelty of the new content, how engaged other people have been by it, geography and possibly also how much someone has paid for a post to appear on your feed.
Infographic depicting the sorts of factors social media algorithms may consider to decide which content to show you.
All that statistics and data science before you've even left the house! And these are just a few examples – statistics and data are hiding in plain sight everywhere, if you are just curious enough to dig deeper. What about the statistics or data science involved in sports team performance, explaining how ChatGPT and AI works, or working out how many people commit crimes? Or what about how we use statistics and data to improve our health and wellbeing, or what we need to watch out for in terms of data privacy and ethics?
Inspiring the next generation
Recent research by Axiom Maths has looked at school pupils’ attitudes towards maths, considering high-attainers versus low-attainers. At age 12-13 (year 8), only just over half of high-attaining students thought that maths was ‘useful’, ‘essential’, or ‘interesting’, while only around 20% or less of low-attaining students thought this. Only around a third of all students found maths ‘fun’. Low-attainers were more likely to find maths ‘stressful’ or ‘boring’ compared to high-attainers, with almost half finding it stressful and a quarter finding it boring.
Data from Axiom Maths. 524 Year 8 pupils (age 12-13) were asked about their views of maths. Pupils were asked to complete the sentence ‘Maths is....’ and were given a selection of words to chose from. They could select as many as applied. Results are provided according to students who were high-attaining versus low-attaining in Year 6. Further details on this research and participant demographics can be found on Axiom Maths.
Here at the RSS we see room for improvement. We recognise that not every student is going to love maths, statistics, or data science, but we strive to work towards a world where more students can see that statistics and data science are interesting, enjoyable, fun, relevant and useful.
The RSS William Guy Lectureship
As part of the William Guy Lectureship, you could play a role in inspiring the next generation. Each academic year we appoint three fellows to inspire young people about the importance of statistics and data – next year, the theme is ‘statistics in plain sight’.
Most statisticians and data scientists work in an area that is in some way relevant to our everyday activities and the world around us. Consider the (hidden) ways your area of expertise impacts the lives of children and young people. Could you change how young people see something they come across daily, shedding light on the statistics and data behind the scenes?
Younger generations may listen to Spotify all day long, but do they know how data influences the charts? They may be glued to social media, but do they really understand the data science forces at play? Are they aware of how ChatGPT strings together answers, or the statistics behind the newest design of their favourite brand of trainers or chocolate bar? How about how statistics contribute to animal conservation? Data and statistics are behind so much in the modern world – so what topic could you inspire the next generation about?
The call for applications for the William Guy Lectureship 2024-25 is currently open, closing on Monday 1st April. Further information on the lectureship and how to apply can be found on the RSS William Guy Lectureship webpages. We are happy to answer any queries at policy@rss.org.uk.