Things to say, professionally, of small significance

May 31st, 2016

The Still Not Significant blog lists lots of ways to mutter, in professional language, if your research findings are statistically marginal. Among them:

What to do if your p-value is just over the arbitrary threshold for ‘significance’ of p=0.05? … The solution is to apply the time-honoured tactic of circumlocution to disguise the non-significant result as something more interesting. The following list is culled from peer-reviewed journal articles in which (a) the authors set themselves the threshold of 0.05 for significance, (b) failed to achieve that threshold value for p and (c) described it in such a way as to make it seem more interesting:

a borderline significant trend (p=0.09)
a clear trend (p<0.09)
a clear, strong trend (p=0.09)
a decreasing trend (p=0.09)
a definite trend (p=0.08)
a favorable trend (p=0.09)
a favourable statistical trend (p=0.09)
a little significant (p<0.1)
a marginal trend (p=0.09)
a marked trend (p=0.07)
a mild trend (p<0.09)
a near-significant trend (p=0.07)
a negative trend (p=0.09)
a nonsignificant trend (p<0.1)
a notable trend (p<0.1)

[see the original article for the full list]


Car Horn Honking Studies (part 2)

May 30th, 2016

Although car horn honking might be viewed by some as a measure of aggression it can also have its positive side. For example in driving simulators, where participants sometimes drive more slowly than they would do on a real road (when not attending to driving) – maybe a horn honk would encourage them to drive more realistically? Investigators Heejin Jeong and Paul Green of the University of Michigan, Industrial and Operations Engineering dept., and the Transportation Research Institute (Driver Interface Group), experimentally tested such a scenario.


A fixed-base National Advanced Driving Simulator MiniSim was used in these experiments (see Figure 2). If drivers were performing manoeuvres that were deemed to be too slow (or too close to other virtual vehicles) they were automatically subjected to honking.

“The 300 ms horn sound sequence consisted of two 100 ms beeps separated by 100 ms. The sound was typical of a car in the U.S. and was found on the Internet. See for an example.“

The results showed that :

“The number of honks per subject varied from 0 to 6 for driving too slowly (less than 25 mi/hr) and 0 to 8 for delayed responses when a traffic light changed from red to green. Older drivers received 2.4 times more honks than younger drivers.”

Lending support to the hypothesis that virtual honking may help to encourage more realistic driving behaviour in simulators :

“Within 5 s after the following vehicle honked between intersections, the mean speed driven increased by 5 mi/hr.”

See: ‘Honking Helps Overcome the Driving Too Slowly Problem in Driving Simulators’ in: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, September 2015, vol. 59 no. 1 1646-1650.

Note: Anecdotal rumours recently heard by Improbable suggest that honking might currently be on the rise in some countries – due a habit that some drivers have acquired: checking their smartphone messages at traffic lights. If you can confirm this, please comment below.

How well scientists understand how to figure out how the brain works…

May 29th, 2016

koerdingAn essay (in The Elusive Self blog) about a demonstration of how little anyone really understands how the brain works:

False functional inference: what does it mean to understand the brain?

A few days ago Eric Jonas and Konrad Kording [pictured here] (J&K) posted a thought-provoking paper on bioRxiv entitled “Could a neuroscientist understand a microprocessor?” It’s been circling round my head for most of the weekend, and prompted some soul searching about what we’re trying to achieve in cognitive neuroscience.

The paper reports on a mischievous set of experiments in which J&K took a simulation of the MOS 6502 microchip (which ran the Apple I computer, and which has been the subject of some fascinating digital archaeology by the team), and then analysed the link between it’s function and behaviour much as we might do for the brain in cognitive and systems neuroscience. The chip’s “behaviour” was its ability to boot and run three different sets of instructions for different games: Donkey Kong, Space Invaders and Pitfall (as a side note, exploring this sent me down the rabbit hole of internet emulations including this one of Prince of Persia which occupied many hours of my childhood). While their findings will not necessarily be surprising for a chip designer, they are humbling for a neuroscientist.

3sect_subBy treating the chip like a mini-brain, albeit one in which the ground truth was fully known, J&K could apply some canonical analysis techniques and see what they revealed. The bottom line is that for most of these analyses, they were either downright misleading or ended up producing trivial results….

(Thanks to Chris Frith for bringing this to our attention.)

BONUS: A recent essay by Robert Epstein, in Aeon: “The empty brain — Your brain does not process information, retrieve knowledge or store memories. In short: your brain is not a computer

A rather colorful insectivorist

May 29th, 2016

Ryan P. Smith, writing in Smithsonian magazine, tells of the book that tells of “The Bizarre Tale of the Tunnels, Trysts and Taxa of a Smithsonian Entomologist“:

A new book details the sensational exploits of Harrison G. Dyar, Jr., a scientist who had two wives and liked to dig tunnels

Dyar instigated fiery feuds with his fellow entomologists. He was concurrently married to two different women. And he dug elaborate, electric-lit tunnels beneath two of his D.C. residences, disposing of the dirt in a vacant lot, or else passing it off as furnace dust or fertilizer.

Long after his death, there were whispers that the tunnels had enabled him to shuttle between his lovers—an urban legend that, while apocryphal, speaks to the mystery in which Dyar seems perennially shrouded…


BONUS: One of our favorites of Dyar’s many scholarly publications: “Note on the secondary abdominal legs in the Megalopygidae,” Harrison G. Dyar,  Journal of the New York Entomological Society, vol. 7, no. 2 (1899): 69-70.


Pedestrian Potential-Collision Standoffs, and Symmetry Breaking

May 28th, 2016

We’ve all experienced this phenomenon: you and someone else are walking towards each other in opposite directions, and you don’t want to collide. Do you shift to the left or to the right? And how should you shift to avoid a standoff? In a new paper on the arXiv, physicists Nickolas Morton and Shaun Hendy of the Department of Physics at University of Auckland have examined this problem through the lens of statistical mechanics. Here is an excerpt from their abstract:

If both make the same choice then passing can be completed with ease, while if they make opposite choices an embarrassing stand- off or collision can occur. Pedestrians who encounter each other frequently can establish “social norms” that bias this decision. In this study we investigate the effect of binary decision-making by pedestrians when passing on the dynamics of pedestrian flows in order to study the emergence of a social norm in crowds with a mixture of individual biases. (…) We construct a phase diagram that shows that a social norm can still emerge provided pedestrians are sufficiently attentive to the choices of others in the crowd. We show that this collective behaviour has the potential to greatly influence the dynamics of pedestrians, including the breaking of symmetry by the formation of lanes.