Group items tagged

Some advice on evaluating claims made on data Bergstrom believes that calling bullshit on data, big or otherwise, doesn't require a statistics degree-only common sense and a few habits of mind. "You don't have to understand all the gears inside a black box in order to evaluate what you're being told," he said. For those who were unable to enroll in INFO 198/BIOL 106B this spring, here is some of his and West's advice:

Medicine's decades-long march toward patient autonomy means patients are often now asked to make the hard decisions - to weigh trade-offs, to grapple with how their values suggest one path over another. This is particularly true when medical science doesn't offer a clear answer: Doctors encourage patients to decide where evidence is weak, while making strong recommendations when evidence is robust. But should we be doing the opposite?People in general are not great at evaluating risk. They worry more about shark attacks than car crashes.

The benefits and harms of medical marijuana can be debated, but more states are legalizing pot, even for recreational use. A new evaluation of marijuana's risks is overdue. Last year, the National Academies of Sciences, Medicine and Engineering released a comprehensive report on cannabis use. At almost 400 pages long, it reviewed both potential benefits and harms. Let's focus on the harms.

Everyone makes claims about what works. Politicians claim that stop-and-search policing will reduce violent crime; friends might assert that vaccines cause autism; advertisers declare that natural food is healthy. A group of scientists describes giving all schoolchildren deworming pills in some areas as one of the most potent anti-poverty interventions of our time. Another group counters that it does not improve children's health or performance at school. Unfortunately, people often fail to think critically about the trustworthiness of claims, including policymakers who weigh up those made by scientists. Schools do not do enough to prepare young people to think critically1. So many people struggle to assess evidence. As a consequence, they might make poor choices. To address this deficit, we present here a set of principles for assessing the trustworthiness of claims about what works, and for making informed choices (see 'Key Concepts for Informed Choices'). We hope that scientists and professionals in all fields will evaluate, use and comment on it.

A piece I wrote on how psychology helps us understand fake news and information seeking. Every day we face complex situations in which the information we need, and who we trust to provide that information, has a very real impact on our lives. How do we evaluate the competing claims of politicians on climate change policy, or Brexit; navigate medical information regarding vaccinating our children; or assess the relative merits of diet versus regular foods in adopting a healthy lifestyle?

How excited would you be about a medication that lowered your risk of cardiovascular death, heart attack or stroke by 1.5%? Excited enough to spend a few thousand dollars a year on the drug? I expect not. What if, instead, the drug reduced those same terrible outcomes by 20%? That's probably enough benefit to interest some in the drug. Well, those statistics come from the same clinical trial, evaluating the same drug. In fact, they present the exact same results, but they simply do it in different ways.

We all do it in journalism. We are taught to write a headline that a) captures what the story is about, and b) captures the reader's attention. Nothing wrong with that. Where the problem comes in is if the headline misleads or misinforms. And, as is so often the case with healthcare topics, that sort of disconnect has the potential to do more harm than good.

Sometimes it's hard to know what statistics are worthy of trust. But we shouldn't count out stats altogether ... instead, we should learn to look behind them. In this delightful, hilarious talk, data journalist Mona Chalabi shares handy tips to help question, interpret and truly understand what the numbers are saying.