Group items tagged

Welcome! This app will help train you to make more accurate, better-calibrated predictions. For each question, you'll be prompted to say what you think the answer is and how confident you are in that answer. You should try to give the right answer whenever you can, but your main goal is to be accurate about how confident you are in each answer. In other words, your goal is to be "well-calibrated," which means that when you say you're 50% confident, you're right about 50% of the time, and when you say you're 80% confident, you're right about 80% of the time, and so on. Nobody is perfectly calibrated, but some people are much better calibrated than others, and a variety of studies suggest you can improve your calibration with the sort of practice this app provides.

Should newspapers be adding confidence intervals to their graphics? Why, she asked, are newspapers like hers hesitant to print confidence intervals, a statistical measure of uncertainty? With the exception of noting sampling error in polling data, newspapers like the Times only show uncertainty when they're forced to - and often to prove the opposite of what point data might show.

Great article discussing experts, their role in democracy, and some of the problems facing expertise. "Part of the problem is that some people think they're experts when in fact they're not. We've all been trapped at a party where one of the least informed people in the room holds court, confidently lecturing the other guests with a cascade of banalities and misinformation. This sort of experience isn't just in your imagination. It's real, and it's called "the Dunning-Kruger effect," after the research psychologists David Dunning and Justin Kruger. The essence of the effect is that the less skilled or competent you are, the more confident you are that you're actually very good at what you do. The psychologists' central finding: "Not only do [such people] reach erroneous conclusions and make unfortunate choices, but their incompetence robs them of the ability to realize it." We are moving toward a Google-fueled, Wikipedia-based collapse of any division between professionals and laypeople."

"I am quite sure now that often, very often, in matters of religion and politics a man's reasoning powers are not above the monkey's," wrote Mark Twain. Having written a book about our most common reasoning errors, I would argue that Twain was being rather uncharitable - to monkeys. Whether we are discussing Trump, Brexit, or the Tory leadership, we have all come across people who appear to have next to no understanding of world events - but who talk with the utmost confidence and conviction. And the latest psychological research can now help us to understand why.

The Media Has A Probability Problem The media's demand for certainty - and its lack of statistical rigor - is a bad match for our complex world.

Data aren't dead, contrary to what some pundits stated post-election [2], rather the limitations of data are not always well reported. While pollsters will be reworking their models following the election, what can media journalists do to improve their overall coverage of statistical issues in the future? First, discuss possible statistical biases, such as errors in sampling and polling, and what impact these might have on the results. Second, always provide measures of uncertainty, and root these uncertainties in real-world examples.