Calling Bullshit in the Age of Big Data

“Our aim in this course is to teach you how to think critically about the data and models that constitute evidence in the social and natural sciences.

Carl T. Bergstrom and Jevin West
Seattle, WA.

I just stumbled on this course they are teaching at the University of Washington.  Yay!  This is the course I would love to teach and it seems more necessary than ever.

They explain on their website: “The world is awash in bullshit. Politicians are unconstrained by facts. Science is conducted by press release. Higher education rewards bullshit over analytic thought…..

We’re sick of it. It’s time to do something, and as educators, one constructive thing we know how to do is to teach people. So, the aim of this course is to help students navigate the bullshit-rich modern environment by identifying bullshit, seeing through it, and combating it with effective analysis and argument.

What do we mean, exactly, by the term bullshit? As a first approximation, bullshit is language, statistical figures, data graphics, and other forms of presentation intended to persuade by impressing and overwhelming a reader or listener, with a blatant disregard for truth and logical coherence.”

Their website has all kinds of useful tools to help us cut through the false narratives and data that look real but are just lies. Check it Out: Click Here


John Oliver on Scientific Studies

John Oliver does a great job in critiquing scientific studies as they often are portrayed by the media.

Click Here

The website Five Thirty Eight posted the results of the American Statistical Association’s expert panel, with the heading: Statisticians Found One Thing They Can Agree On: It’s Time to Stop Misusing P-Values.

While there were heated discussions about what the p-value means, the authors stated, “If there’s one takeaway from the ASA statement, it’s that p-values are not badges of truth and p < 0.05 is not a line that separates real results from false ones. They’re simply one piece of a puzzle that should be considered in the context of other evidence.”

Click Here

Stressed Out?

Science stat’s published research about Americans and stress, looking at several demographic and situational factors that might contribute to stress. Click here for article

stress data
They described the methodology:
“About the study:

Interviews were conducted via telephone (including both landline and cell phone) between March 3 and April 8, 2014, among a nationally representative sample of 2,505 adults age 18 and older. The interviews were conducted in English and Spanish. To compensate for known biases and variations in probability of selection within and across households, sample data were weighed by household size, cell phone/landline use and demographics to reflect the true population. Random-digit dialing, replicate subsamples, and systematic respondent selection within households, were used to ensure that the sample is representative.”

What surprises you? What does not? What factors might explain variations in reported stress levels by gender or income? What other factors might affect stress levels that they did not ask about?

Spinning Upward Mobility

Today (January 23, 2014), the New York Times had an article with the headline: “Upward Mobility Has Not Declined.” Reading just the headline, you might wonder what all the fuss is about. The lead paragraph states:
“The odds of moving up — or down — the income ladder in the United States have not changed appreciably in the last 20 years, according to a large new academic study that contradicts politicians in both parties who have claimed that income mobility is falling.”

But is the headline accurate? Not really. The author of the study, it appears, made the case that “Despite less discrimination of various kinds and a larger safety net than in previous decades, the odds of escaping the station of one’s birth are no higher today than they were decades ago.”

So, while mobility rates have not declined, they have not increased either. The more accurate summary would be that upward mobility has not changed in the past 2 decades. Continue reading »

Do Clinical Trials Work?

pillsA NY Times article asking “Do Clinical Trials Work?” stirred up lots of questions about the challenges of using experimental designs. Read here Clinical trials (also called experimental designs) are often referred to as “the gold standard” of research. In social science, they are hard to do; when they are used, the results are often inconclusive. Somehow, I thought science might be different, but at least in terms of health research on drugs, the results are also often disappointing, according to the author Clifton Leaf. Continue reading »

Asking Tough Questions about Research Studies

I am not the only one who is trying to make it easier for people to make sense of research results. For those who are interested in health and nutrition, the number of studies can feel overwhelming, not to mention conflicting.  Here is a webpost from Chris Kresser about how to read and understand scientific research. Interesting comments as well. Asking tough questions are essential.
  Check it out here: Kresser: How to read and understand scientific research

Kresser provides this link to more information about research put together by the Cancer Information and Support Network. It provides excellent information.
Check it out here: How Cancer is Studied

Fact is Dead?

Driving home from the store, a story came on about how Facts have died.  So I googled it.  Rex Huppke, a Chicago Tribune reporter wrote the story,

Leading with a headline:

Facts, 360 B.C.-A.D. 2012

In memoriam: After years of health problems, Facts has finally died.

April 19, 2012  By Rex W. Huppke, Chicago Tribune reporter
He wrote:
“To the shock of most sentient beings, Facts died Wednesday, April 18, after a long battle for relevancy with the 24-hour news cycle, blogs and the Internet. Though few expected Facts to pull out of its years-long downward spiral, the official cause of death was from injuries suffered last week when Florida Republican Rep. Allen West steadfastly declared that as many as 81 of his fellow members of the U.S. House of Representatives are communists….

Facts is survived by two brothers, Rumor and Innuendo, and a sister, Emphatic Assertion.  Services are alleged to be private. In lieu of flowers, the family requests that mourners make a donation to their favorite super PAC.”

Article can be found at: Facts is Dead

Continue reading »

Another reality check: taxes and job creation

I stumbled on this interesting chart. The data is reported to be from the Bureau of Labor Statistics.

The blogger writes: “In theory, the GOP is so committed to resisting tax hikes because it’s so committed to creating jobs. “The fact is you can’t tax the very people that we expect to invest in the economy and create jobs,” says Speaker John Boehner. But Michael Linden’s chart comparing average annual job creation at different marginal tax rates begs to differ:”

Blog post can be found at: Continue reading »