Archive for Nature

measuring honesty, with p=.006…

Posted in Books, Kids, pictures, Statistics with tags , , , , , on April 19, 2016 by xi'an


Simon Gächter and Jonathan Schulz recently published a paper in Nature attempting to link intrinsic (individual) honesty with a measure of corruption in the subject home country. Out of more than 2,500 subjects in 23 countries. [I am now reading Nature on a regular basis, thanks to our lab subscribing a coffee room subscription!] Now I may sound naïvely surprised at the methodological contents of the paper and at a publication in Nature but I never read psychology papers, only Andrew’s rants at’em!!!

“The results are consistent with theories of the cultural co-evolution of institutions and values, and show that weak institutions and cultural legacies that generate rule violations not only have direct adverse economic consequences, but might also impair individual intrinsic honesty that is crucial for the smooth functioning of society.”

The experiment behind this article and its rather deep claims is however quite modest: the authors asked people to throw a dice twice without monitoring and rewarded them according to the reported result of the first throw. Being dishonest here means reporting a false result towards a larger monetary gain. This sounds rather artificial and difficult to relate to dishonest behaviours in realistic situations, as I do not see much appeal in cheating for 50 cents or so. Especially since the experiment accounted for a difference in wealth backgrounds, by adapting to the hourly wage in the country (“from $0.7 dollar in Vietnam to $4.2 in the Netherlands“). Furthermore, the subjects of this experiment were undergraduate students in economics departments: depending on the country, this may create a huge bias in terms of social background, as I do not think access to universities is the same in Germany and in Guatemala, say.

“Our expanded scope of societies therefore provides important support and qualifications for the generalizability of these theories—people benchmark their justifiable dishonesty with the extent of dishonesty they see in their societal environment.”

The statistical analysis behind this “important support” is not earth-shattering either. The main argument is based on the empirical cdfs of the gain repartitions per country (in the above graph), with tests that the overall empirical cdf for low corruption countries is higher than the corresponding one for high corruption countries. The comparison of the cumulated or pooled cdf across countries from each group is disputable, in that there is no reason the different countries have the same “honesty” cdf. The groups themselves are built on a rough measure of “prevalence of rule violations”. It is also rather surprising that for both groups the percentage of zero gain answers is “significantly” larger than the expected value of 2.8% if the assumption of “justified dishonesty” holds. In any case, there is no compelling argument as to why students not reporting the value of the first dice would naturally opt for the maximum of the two dices. Hence a certain bemusement at this paper appearing in Nature and even deserving an introductory coverage in the first part of the journal…

duck, duck, …magnetic duck

Posted in Books, Kids, pictures, Travel with tags , , , , , on April 17, 2016 by xi'an

“Mallards in tight formation tends to face either north or south when landing. Because vision alone cannot prevent collision between these high-speed flyers, the ducks use sensors in their eyes, beaks and ears to align themselves to Earth’s magnetic field.” Nature, vol. 531, 31 March 2016

reproducibility

Posted in Books, Statistics with tags , , , , , , , , on December 1, 2015 by xi'an

WariseWhile in Warwick this week, I borrowed a recent issue (Oct. 08, 2015) of Nature from Tom Nichols and read it over diners in a maths house. Its featured topic was reproducibility, with a long initial (or introductory) article about “Fooling ourselves”, starting with an illustration from Andrew himself who had gotten a sign wrong in one of those election studies that are the basis of Red State, Blue State. While this article is not bringing radically new perspectives on the topic, there is nothing shocking about it and it even goes on mentioning Peter Green and his Royal Statistical Society President’s tribune about the Sally Clark case and Eric-Jan Wagenmakers with a collaboration with competing teams that sounded like “putting one’s head on a guillotine”. Which relates to a following “comment” on crowdsourcing research or data analysis.

I however got most interested by another comment by MacCoun and Perlmutter, where they advocate a systematic blinding of data to avoid conscious or unconscious biases. While I deem the idea quite interesting and connected with anonymisation techniques in data privacy, I find the presentation rather naïve in its goals (from a statistical perspective). Indeed, if we consider data produced by a scientific experiment towards the validation or invalidation of a scientific hypothesis, it usually stands on its own, with no other experiment of a similar kind to refer to. Add too much noise and only noise remains. Add too little and the original data remains visible. This means it is quite difficult to calibrate the blinding mechanisms in order for the blinded data to remain realistic enough to be analysed. Or to be different enough from the original data for different conclusions to be drawn. The authors suggest blinding being done by a software, by adding noise, bias, label switching, &tc. But I do not think this blinding can be done blindly, i.e., without a clear idea of what the possible models are, so that the perturbed datasets created out of the original data favour more one of the models under comparison. And are realistic for at least one of those models. Thus, some preliminary analysis of the original or of some pseudo-data from each of the proposed models is somewhat unavoidable to calibrate the blinding machinery towards realistic values. If designing a new model is part of the inferential goals, this may prove impossible… Again, I think having several analyses run in parallel with several perturbed datasets quite a good idea to detect the impact of some prior assumptions. But this requires statistically savvy programmers. And possibly informative prior distributions.

how can we tell someone “be natural”? [#2]

Posted in Books, Kids, pictures, University life with tags , , , , , , , , , on November 17, 2013 by xi'an

Following my earlier high school composition (or, as my daughter would stress, a first draft of vague ideas towards a composition!), I came upon an article in the Science leaflet of Le Monde (as of October 25) by the physicist Marco Zito (already commented on the ‘Og): “How natural is Nature?“. The following is my (commented) translation of the column, I cannot say I understand more than half of the words or hardly anything of its meaning, although checking some Wikipedia entries helped (I wonder how many readers have gotten to the end of this tribune)

The above question is related to physics in that (a) the electroweak interaction scale is about the mass of Higgs boson, at which scale [order of 100GeV] the electromagnetic and the weak forces are of the same intensity. And (b) there exists a gravitation scale, Planck’s mass, which is the energy [about 1.2209×1019GeV] where gravitation [general relativity] and quantum physics must be considered simultaneously. The difficulty is that this second fundamental scale differs from the first one, being larger by 17 orders of magnitude [so what?!]. The difference is puzzling, as a world with two fundamental scales that are so far apart does not sound natural [how does he define natural?]. The mass of Higgs boson depends on the other elementary particles and on the fluctuations of the related fields. Those fluctuations can be very large, of the same order as Planck’s scale. The sum of all those terms [which terms, dude?!] has no reason to be weak. In most possible universes, the mass of this boson should thus compare with Planck’s mass, hence a contradiction [uh?!].

And then enters this apparently massive probabilistic argument:

If you ask passerbys to select a number each between two large bounds, like – 10000 and 10000, it is very unlikely to obtain exactly zero as the sum of those numbers. So if you observe zero as the sum, you will consider the result is not «natural» [I’d rather say that the probabilistic model is wrong]. The physicists’ reasoning so far was «Nature cannot be unnatural. Thus the problem of the mass of Higgs’ boson must have a solution at energy scales that can be explored by CERN. We could then uncover a new and interesting  physics». Sadly, CERN has not (yet?) discovered new particles or new interactions. There is therefore no «natural» solution. Some of us imagine an unknown symmetry that bounds the mass of Higgs’ boson.

And a conclusion that could work for a high school philosophy homework:

This debate is typical of how science proceeds forward. Current theories are used to predict beyond what has been explored so fat. This extrapolation works for a little while, but some facts eventually come to invalidate them [sounds like philosophy of science 101, no?!]. Hence the importance to validate through experience our theories to abstain from attributing to Nature discourses that only reflect our own prejudices.

This Le Monde Science leaflet also had a short entry on a meteorite called Hypatia, because it was found in Egypt, home to the Alexandria 4th century mathematician Hypatia. And a book review of (the French translation of) Perfect Rigor, a second-hand biography of Grigory Perelman by Martha Gessen. (Terrible cover by the way, don’t they know at Houghton Mifflin that the integral sign is an elongated S, for sum, and not an f?! We happened to discuss and deplore with Andrew the other day this ridiculous tendency to mix wrong math symbols and greek letters in the titles of general public math books. The title itself is not much better, what is imperfect rigor?!)  And the Le Monde math puzzle #838

Confronting intractability in Bristol

Posted in pictures, Running, Statistics, Travel, University life, Wines with tags , , , , , , , , , , , , on April 18, 2012 by xi'an

Here are the (revised) slides of my talk this afternoon at the Confronting Intractability in Statistical Inference workshop in Bristol, supported by SuSTain. The novelty is in the final part, where we managed to apply our result to a three population genetic escenario using one versus two δμ summary statistics. This should be the central new example in the incoming revision of our paper to Series B.

More generally, the meeting is very interesting, with great talks and highly relevant topics: e.g., yesterday, I finally understood what transportation models meant (at the general level) and how they related to copula modelling, saw a possible connection from computer models to ABC, got inspiration to mix Gaussian processes with simulation output, and listened to the whole exposition of Simon Wood’s alternative to ABC (much more informative than the four pages of his paper in Nature!). Despite (or due to?) sampling Bath ales yesterday night, I even woke up early enough this morning to run over and under the Clifton suspension bridge, with a slight drizzle that could not really be characterized as rain…

not yet another musk ox in my garden!

Posted in Statistics, University life with tags , , , , , , , , on November 22, 2011 by xi'an

Here is a map of the estimated range of the musk ox at various epochs, hence meaning one could indeed have visited my garden about 30,000 years ago… This map is extracted from a very interesting paper by Lorenzen et al. that just appeared in Nature. The main theme of the paper is to determine whether or not human intervention had an impact on the total or partial extinction of species on Earth. Their conclusion is that this only seems to be the case for European horses and bisons. This came to my attention because of Scott Sisson’s tweet on this paper. Given that it involves ABC technology, in particular ABC model choice based on solely four summary statistics (nucleotide diversity, Tajima’s D, haplotypic diversity, and Fst) and posterior probabilities. I wonder if this fits our requirement for convergence.

Testing and significance

Posted in R, Statistics, University life with tags , , , , , , , on September 13, 2011 by xi'an

Julien Cornebise pointed me to this Guardian article that itself summarises the findings of a Nature Neuroscience article I cannot access. The core of the paper is that a large portion of comparative studies conclude to a significant difference between protocols when one protocol result is significantly different from zero and the other one(s) is(are) not…  From a frequentist perspective (I am not even addressing the Bayesian aspects of using those tests!), under the null hypothesis that both protocols induce the same null effect, the probability of wrongly deriving a significant difference can be evaluated by

> x=rnorm(10^6)
> y=rnorm(10^6)
> sum((abs(x)<1.96)*(abs(y)>1.96)*(abs(x-y)<1.96*sqrt(2)))
[1] 31805
> sum((abs(x)>1.96)*(abs(y)<1.96)*(abs(x-y)<1.96*sqrt(2)))
[1] 31875
> (31805+31875)/10^6
[1] 0.06368

which moves to a 26% probability of error when x is drifted by 2! (The maximum error is just above 30%, when x is drifted by around 2.6…)

(This post was written before Super Andrew posted his own “difference between significant and not significant“! My own of course does not add much to the debate.)

Follow

Get every new post delivered to your Inbox.

Join 1,023 other followers