Posted on

On inference and statistical significance

Friday rabbit hole caveats be damned healed, a reference to p-values in my readings this week struck a chord for ready digression.

I interviewed a statistics researcher [podcast versions] a few years ago who served as an co-editor on special journal issue dedicated to the (mis)use of statistical significance in research, particularly psychology research and specifically the phenomenon know as p-hacking:

a little more explanation of the null hypothesis and how it relates to other flaws in the typical way psychology researchers have handled statistical analysis over the past several decades. Roughly, our research often comes down to finding differences between groups of participants on some variable of interest (Are boys better at math than girls?) or correlations among two or more variables (Does suicide risk rise as poverty increases?). The null hypothesis is the assumption we then make that there are no such differences or correlations in the populations from which our data were drawn, and we compute the probability that we would have found data with differences or correlations as large as we actually did if the null hypothesis were true. If that probability (called a “p-value”) is less than some specified value, typically .05, then we reject the null hypothesis and conclude that the differences or correlations we found are probably real. This is known as a statistically “significant” result. If the p-value is greater than .05, then we fail to reject the null hypothesis, for lack of convincing evidence otherwise.
Research that fails to reject the null hypothesis rarely gets published in scientific journals. Likewise, research that merely replicates rejections that were found in earlier research rarely gets published. As a consequence, there is a high professional premium on testing questions that have not been previously published, and on rejecting the null hypothesis.

The widespread adoption of these customs has unintentionally encouraged a whole series of inadvisable research practices, which have led to trouble. For instance, because most studies that do not find significant effects go unpublished, we don’t know whether the findings of the published research are real or just the mistakes that our chosen p-value allows to slip through (the “file-drawer problem”). This problem might be attenuated if we published efforts to replicate previous findings, but that kind of research is rarely accepted by journals.

Note the generosity embedded in the term ‘inadvisable.’ Hmm.

 

Posted on

Means as Message

Digital-Billboards-Mockup

The Times returns to a past series on driving distractions to look at LED billboards:

Some cities and states are debating whether to prohibit or regulate this new form of advertising for fear that it can distract drivers and raise the rate of accidents.

A new study concludes that there are environmental reasons to avoid digital billboards as well. Digital billboards, which are made of LED lights, consume lots of energy and are made of components that will turn into e-waste once the billboard’s life has ended.

But wait, you ask, isn’t LED lighting quite energy-efficient? True, notes the report’s author, Gregory Young, a Philadelphia-based architectural designer and urban planner. But traditional billboards are lit by only two or three lamps, albeit inefficient ones, and only at night. By contrast, digital billboards have hundreds if not thousands of LEDs, which are illuminated day and night. And LEDs function poorly at high temperatures, so the signs need a cooling system.

This would seem to be the worst of both worlds so, of course: we all want one. Turn your interstate into a lame version of the Vegas strip. Really, it’s another brilliant move by the outdoor advertising industry, who you should assume has all your best interests at heart – they’re looking out for you, just like all the health care companies and financial planning institutions that pay their biggest fees. But even outside of the inherent dangers of looking up from your iPad burrito Four Loko steering wheel and general eco-lessness of these forms of advertising, I’m more concerned about the sort of dull feeling about our surroundings that actually emanate from them, much more strongly than any other intended message. Beaming lights in articulation of a come-in and/or otherwise recognizable logo design is our current version of anti-beauty. And as much as LED billboards seem like some sort of natural evolution of the kind of eye-poison to which we’ve all become so accustomed and accommodating, they’re not. They are their own form of dystopia. I.e., an actual sign of something.

Since some call this the season of beauty, everyone should just take some time and re-load on the most agreeable things you can find. It will help us not be so accepting of these kinds of invasions into our mental space, especially through the pollution of actual space, using actual pollution to do it. Three birds: meet my friend, stone.

Posted on

Fun in the Hot House

Listening to the Stooges’ Fun House at the bar last night then biking home late, I was conscious of an extended moment amidst the swirl of information and goings-on. If you take so much in and do not take some time away to think and cavort, it can all be overwhelming. A sample of what’s around you:

Juan Cole on the UN call for a ceasefire and settler colonialism.

Well-chosen words on the aforementioned Obama stimulus package.

A fire burning for forty-six years?

The search for signs and meanings.

Astrophysicist/author discusses the implications of death by black hole.

DH Lawrence on Democracy (‘flip’ to page 63).

1997 Salon interview with Robert Hughes.

And finally, just a few things to look into.