Novel statistics can be hard to communicate. — In my voluntary role, I went to Galway in Ireland to talk about statistical communication. Pandemic experiences in Ireland and Britain give examples of challenges to conveying numbers. Statistics is the study of data. That covers its collection, management, analysis, interpretation, and communication. The last step — communication —…

Much can go wrong when making data visualisations. — Creating graphs is a key way to communicate statistics. There are many steps to this process, and graphs have a grammar. Studying bad examples is often a good way to learn. Through failure, gain insights into the means of success. Google cards The Google card for reported Covid-19 surveillance deaths is inaccurate…

What went wrong with a graph about intensive care in US states? — The Covid-19 pandemic has put great urgency on visualising data and numbers. That flurry leads to some great and poor graphs. One example of bad graphing appears to come from Morgan Stanley. The graph shows intensive care patients in ‘closed’ and ‘open’ US states. …

Gaps between confirmed cases and PCR-positive estimates grow. — On 1st April 2022, free Covid-19 testing for the general public in England ended. In Wales, some free testing capacity continues to the end of June. For people in Scotland, free rapid tests will not be available from 18th April. Under a renewed definition, UK confirmed case figures are counts…

Analysis from the Office for National Statistics compares European nations. — In my co-written book Covid by Numbers, a graph shows relative age-standardised mortality. The graph in the book has a production error, where the UK lines do not have correct alignment. The original version, made in R, looks like: What are relative age-standardised mortality rates? To calculate age-standardised mortality, we…

How could we show the uncertainty in statistics? — Uncertainty is an integral part of statistics. Data can come from random processes, or miss entries. Model assumptions can take many plausible values. Different methods can lead to different estimates and outputs. In August 2020, the Government Statistical Service hosted a webinar on communicating uncertainty. That…

How do constraints affect the chance teams will face each other? — The televised World Cup draw selected groups for the men’s football competition. There are three good properties for a drawing system to have: Fairness: no team should have greater chances than others of a ‘tough’ group. Balance: the groups should be at a similar competitive level. Uniformity: the probability of…

The numbers of deaths increase, whilst mortality rates decline. — Why were the numbers of deaths in Australia higher in 2021 than in the previous year? Three factors influence death counts in a population: Population size: a larger group is more likely to experience people dying. Age structure: mortality risks increase with age, so older populations have more deaths. Mortality…

What share of UK adults gave the right answer to a statistical question? — Classical statistics thinks of probability as the long-run frequency of events. The Bayesian approach considers probability as a degree of belief. The language of probability then describes uncertainty in unknown quantities. The Royal Statistical Society commissioned a survey of the public, asking this question: Question 1: If you toss a…