The Truth about Statistics
With the release of Jersey’s most recent Labour Market Statistics hot on our heels, and with the CIPR Channel Islands Forum having recently
focused on the use of ‘open data, it’s an opportune time to consider how we as public relations and communications specialists are sometimes left in a state of mystification following the publication and use of statistics in public fora.
When we look at the many different ways of which media interpret the same set of stats it becomes clear that people will use data to support their own beliefs. Indeed, it was commented at that CIPR Forum that, in light of the UK EU referendum result and what we are currently seeing in the US Presidential race, we are living in a ‘post factual’ world where emotion is seemingly more important than fact. It’s very simple to take one side of a set of stats and use that to support a view that is already favoured or desired.
In 2011, Anthony Bastardi, Eric Uhlmann, and Lee Ross conducted a study to prove the claim that people will believe what they want to believe, regardless if there is contradicting data available that may be stronger than the research they hold dear.
The study, Wishful Thinking: Belief, Desire, and the Motivated Evaluation of Scientific Evidence, examines a group of participants who all expected to have children in the near future and who all believed that caring for young children at home was better for the child than sending them to an outside day care. One half of these participants, however, expected they would send their child to day care someday, while the other half were people who expected they would keep their child at home.
The method of the experiment was to have everyone read one study that supported the conclusion that home care really is better than day care, and then they all read another study that supports the conclusion that day care is better than homecare. Each study had varying methods to reach their conclusions. Afterwards, the participants were asked to evaluate the studies for whether the methods were valid and whether the studies were convincing.
As expected, the half of the participants who believed that home care is better and planned to care for their children at home supported the results of the study which supported homecare for children. On that same note, the half of the participants who believed home care was best but planned to send their children to day care found that the study which supported day care was more convincing.
Keeping the findings of this study in mind it’s important to look at data and statistics with an open mind and to consider all the information that is available. The Chartered Institute of Public Relations (CIPR) released this skills guide on statistics over the summer as a part of their #summerofCPD campaign. This guide gives some sound advice of how to approach statistics as a public relations practitioner and why it’s important to use statistics well.
A few key points from the guide to keep at the forefront of your mind when it comes to stats is to be sure to define things clearly. Ensure that your audience will be reading the same exact message that you intended to portray when you wrote it out. Also, remember that correlation doesn’t always lead to causation. In other words, two things that may seem like they are dependent on each other doesn’t always mean that they are.
So, keep these insights and tips in mind the next time a large set of data is released and the differing conclusions seems daunting. They may just enlighten the real message being portrayed in the ever complex language of statistics.