A wide range of audience, including academics, students, school teachers and general public, heard Neil Sheldon (chair of the Teaching Statistics Trust and former vice president of the RSS) deliver the 2019 Teaching Statistics Trust lecture at the University of Plymouth, 25 September 2019.
Neil began by reviewing briefly the development of statistics from being a formulae-and-calculation-based discipline to one where these components are carried out by increasingly sophisticated software capable of processing very large data sets (big data). This move has simultaneously meant that teachers of statistics need to change their focus from numbers to language.
Statistics often uses language where some words have different meaning compared with their everyday use. This implies that parallel meanings often make it harder for students to understand technical concepts; indeed research shows that teaching with a richer vocabulary can help to overcome problems of understanding. Neil illustrated this by pointing out that the word ‘significant’ means very different things in everyday use compared with its use in statistics.
There has been much debate over the use of ‘significant’ in statistics literature; see, for example, the American Statistical Association statement about its use. Neil argued cogently that the statistical use of ‘significant’ should be abolished and replaced by careful use of the word ‘outlier’. This would be in the context of talking about the probability of observed data given a null hypothesis; however, teachers should be aware of the often-confused likelihood of a null hypothesis given observed data!
He showed how statistical data are routinely misunderstood and misinterpreted in the media. In most cases the errors arise, not from the numbers themselves, but from the confused and inaccurate language used to comment on them. He used examples from a publication of the Nationwide Building Society where even the word ‘average’ was misused. Other misuses included comments relating to errors in GCE grades by awarding bodies. Statistics is more than just an academic discipline, Neil said; it is a vital element of citizenship: we all need statistical understanding to make sense of the world around us. Clear language is essential to clear thought.
This lecture was a masterclass in showing why and how teachers, students and citizens need to understand statistics better; in formulating enquiries, interpreting data, reaching trustworthy conclusions and communicating them effectively.
The lecture was very well received, and generated much discussion afterwards.