Graphic presentation of data & understanding of stats can be a matter of life & death. Just learned something: Those Hurricane Maps Don’t Mean What You Think They Mean - The New York Times https://www.nytimes.com/interactive/2019/08/29/opinion/hurricane-dorian-forecast-map.html">https://www.nytimes.com/interacti...
According to the Times description, those maps are basically confidence intervals -- which almost everyone, including social scientists, misunderstand (just like they misunderstand statistical significance).
"Significance" in a null hypothesis test, e.g., .05, isn& #39;t the probability there& #39;s an effect given the data (a Bayesian posterior). It& #39;s the prob of getting the data given there& #39;s no effect (a likelihood). Study: 80% of profs teaching stats get this wrong. http://www.onemol.org.uk/Gigerenzer-2004.pdf">https://www.onemol.org.uk/Gigerenze...
Similarly, a 95% confidence interval doesn& #39;t mean there& #39;s a .95 prob the true value is somewhere inside it (a Bayesian concept). It means 95% of the time you& #39;ve placed the interval over the true value (given several assumptions). Not the same thing.
Hurricane maps don& #39;t show the probable path of the eye + size of the storm. They are regions that are likely to include the storm, & fatten over time because our uncertainty, not the storm, grows. An important distinction. Excellent illustrations in the NYT article.