Archive for Science

gender gaps

Posted in Statistics, University life with tags , , , , , , , , , , on March 31, 2018 by xi'an

Two of my colleagues [and co-authors] at Dauphine, Elyès Jouini and Clotilde Napp, published a paper in Science last week (and an associated tribune in Le Monde which I spotted first) about explaining differences in national gender inequalities in maths (as measured by PISA) in terms of the degree of overall inequality in the respective countries. Gaps in the highest maths performer sex ratio. While I have no qualm about the dependency or the overall statistical cum machine learning analysis (supported by our common co-author Jean-Michel Marin), and while I obviously know nothing about the topic!, I leisurely wonder at the cultural factor (which may also partly explain for the degree of inequality) when considering that the countries at the bottom of the above graphs are rather religious (and mostly catholic). I also find it most intriguing that the gender gap is consistently reversed when considering higher performer sex ratio for reading, because mastering the language should be a strong factor in power structures and hence differences therein should also lead to inequalities…

March(es) for Science

Posted in Statistics with tags , , , , , , , on April 22, 2017 by xi'an

Today there are around 500 marches for Science organised around the World (incl. on in Kangerlussuaq, Qeqqata, Greenland!). Primarily to protest the unprecedented attacks of trumpism on science, scientific values, and scientists, and not only through budget cuts, agency closures, public data erasures, but also denegation of scientific expertise and data to advance financial and partisan interests against climate, water preservation, minorities rights, women equality, and international relations. Being now at a remote retreat in Northern Wales, I will walk virtually at the Cardiff March for Science.

an unexpected outlet for a final message

Posted in Books, Kids, pictures with tags , , , , , on January 19, 2017 by xi'an

President Barack Obama has once again raised the epitomé of cool by writing a tribune in Science entitled The irreversible momentum of clean energy. A few days before leaving his office.

“…evidence is mounting that any economic strategy that ignores carbon pollution will impose tremendous costs to the global economy and will result in fewer jobs and less economic growth over the long term.” B. Obama, 13 January, 2017

I do not know how many other US presidents or would-be presidents have written in Science or equivalent journals (maybe Abraham Lincoln when seeking alternatives to sperm whale oil), but I doubt his immediate successor will be one of these. So, goodbye Mr. President! And sorry to see you leave…

a discovery that mean can be impacted by extreme values

Posted in University life with tags , , , , , , on August 6, 2016 by xi'an

A surprising editorial in Nature about the misleading uses of impact factors, since as means they are heavily impacted by extreme values. With the realisation that the mean is not the median for skewed distributions…

To be fair(er), Nature published a subsequent paper this week about publishing additional metrics like the two-year median.

Le Monde and the replication crisis

Posted in Books, Kids, Statistics with tags , , , , , , , , , , , , , , , on September 17, 2015 by xi'an

An rather poor coverage of the latest article in Science on the replication crisis in psychology in Le Monde Sciences & Medicine weekly pages (and mentioned a few days ago on Andrew’s blog, with the terrific if unrelated poster for Blade Runner…):

L’étude repose également sur le rôle d’un critère très critiqué, la “valeur p”, qui est un indicateur statistique estimant la probabilité que l’effet soit bien significatif.

As you may guess from the above (pardon my French!), the author of this summary of the Science article (a) has never heard of a p-value (which translates as niveau de signification in French statistics books) and (b) confuses the probability of exceeding the observed quantity under the null with the probability of the alternative. The remainder of the paper is more classical, pointing out the need for preregistered protocols in experimental sciences. Even though it mostly states evidence, like the decrease in significant effects for prepublished protocols. Apart from this mostly useless entry, rather interesting snapshots in the issue: Stephen Hawking’s views on how information could escape a black hole, an IBM software for predicting schizophrenia, Parkinson disease as a result of hyperactive neurons, diseased Formica fusca ants taking some harmful drugs to heal, …

les sciences face aux créationnismes [book review]

Posted in Books with tags , , , , , , on March 9, 2014 by xi'an

I spotted this small book during my last visit to CBGP in Montpellier, and borrowed it from the local librarian. It is written (in French) by Guillaume Lecointre, who is professor of Biology at the Muséum National d’Histoire Naturelle in Paris, specialised in population evolution and philogenies. The book is published by Editions Quae, a scientific editor supported by four founding French institutes (CIRAD, IFREMER, INRA and IRSTEA), hence no wonder I would spot it in an INRA lab. The theme of the book is not to argue against creationism and intelligent design theories, but rather to analyse how the debates between scientists—interestingly this term scientist sounds much more like a cult in English than the French noun scientifique— and creationists are conducted and to suggest how they should be conducted. While there are redundancies in the text, I found the overall argumentation quite convincing, with the driving lines that creationists are bypassing the rules of scientific investigation and exchange to bring the debate at a philosophical or ideological level foreign to science definition. Lecointre deconstructs the elements put forward in such debates, from replacing the incompleteness of the scientific knowledge and the temporary nature of scientific theories with a total relativism, to engaging scientific supporters from scientific fields not directly related with the theory of evolution, to confusing methodological materialism with philosophical materialism and more fundamentally to imply that science and scientific theories must have a moral or ideological content, and to posturing as anti-establishment and anti-dogmatic free minds… I also liked the points that (a) what really drives the proponents of intelligent design is a refusal of randomness in the evolution, without any global or cosmic purpose; (b) scientists are very ill-prepared to debate with creationists, because the later do not follow a scientific reasoning; (c) journalists are most often contributing to the confusion by picking out-of-their-field “experts” and encouraging the relativity argument. Hence a reasonable recommendation to abstain from oral debates and to stick to pointing out the complete absence of scientific methodology in creationists’ arguments. (Obviously, readers of Alan Sokal’s Beyond the Hoax will be familiar most of the arguments produced in les sciences face aux créationnismes.)

epidemiology in Le Monde

Posted in Books, Statistics, University life with tags , , , , , , , , , on February 19, 2012 by xi'an

Quite an interesting weekend Le Monde issue: a fourth (2 pages!) of the science folder is devoted to epidemiology… In the statistical sense. (The subtitle is actually Strengths and limitations of Statistics.) The paper does not delve into technical statistical issues but points out the logical divergence between a case-by-case study and an epidemiological study. The impression that the higher the conditioning (i.e. the more covariates), the better the explanation is a statistical fallacy some of the opponents interviewed in the paper do not grasp. (Which reminded me of Keynes seemingly going the same way.) The short paragraph written on causality and Hill’s criteria is vague enough to concur to the overall remark that causality can never been proved or disproved… The fourth examples illustrating the strengths and limitations are tobacco vs. lung cancer, a clear case except for R.A. Fisher!, mobile phones vs. brain tumors, a not yet conclusive setting, hepatitis B vaccine vs. sclerosis, lacking data (the pre-2006 records were destroyed for legal reasons), and leukemia vs. nuclear plants, with a significant [?!] correlation between the number of cases and the distance to a nuclear plant. (The paper was inspired by a report recently published by the French Académie de Médecine on epidemiology in France.) The science folder also includes a review of a recent Science paper by Wilhite and Fong on the coercive strategies used by some journals/editors to increase their impact factor, e.g., “you cite Leukemia [once in 42 references]. Consequently, we kindly ask you to add references of articles published in Leukemia to your present article”.