A recent paper: Anders Eklunda, Thomas E. Nicholsd, and Hans Knutssona, Cluster failure: Why fMRI inferences for spatial extent have inflated false-positive rates.
doi: 10.1073/pnas.1602413113, bit.ly/29j7dKf
sends a pretty grim message:
The most widely used task functional magnetic resonance imaging (fMRI) analyses use parametric statistical methods that depend on a variety of assumptions. In this work, we use real resting-state data and a total of 3 million random task group analyses to compute empirical familywise error rates for the fMRI software packages SPM, FSL, and AFNI, as well as a nonparametric permutation method. For a nominal familywise error rate of 5%, the parametric statistical methods are shown to be conservative for voxelwise inference and invalid for clusterwise inference. Our results suggest that the principal cause of the invalid cluster inferences is spatial autocorrelation functions that do not follow the assumed Gaussian shape. By comparison, the nonparametric permutation test is found to produce nominal results for voxelwise as well as clusterwise inference. These findings speak to the need of validating the statistical methods being used in the field of neuroimaging.
Implications are very serious:
Functional MRI (fMRI) is 25 years old, yet surprisingly its most common statistical methods have not been validated using real data. Here, we used resting-state fMRI data from 499 healthy controls to conduct 3 million task group analyses. Using this null data with different experimental designs, we estimate the incidence of significant results. In theory, we should find 5% false positives (for a significance threshold of 5%), but instead we found that the most common software packages for fMRI analysis (SPM, FSL, AFNI) can result in false-positive rates of up to 70%. These results question the validity of some 40,000 fMRI studies and may have a large impact on the interpretation of neuroimaging results.
Alas, too many people think that everything is normal…
A paper by Chris Havergal in Times Higher Education. Some quotes:
The first-ever release of Ucas data at institutional level shows that the University of Cambridge admitted only 65 18-year-olds from the UK’s most disadvantaged neighbourhoods in 2015, while it gave places to 1,260 learners from the most advantaged backgrounds. Taken as a proportion of the total size of these groups, this meant that the most privileged students were 16 times more likely to win a place.
The overall ratio for the Russell Group of highly selective institutions was 7.7, but this remained significantly higher than the UK-wide average of 2.45. At providers with the lowest entry standards, the most privileged students were only 12 per cent more likely to get in.
Read the whole article.
I’d like to draw your attention to a new book: ‘Teaching Mathematics for Social Justice: Meaningful Projects for the Secondary Mathematics Classroom’. The aim of the book is to share teaching resources and ideas generated from the TMSJ Research Project (a participatory action research project). The book was published by the Association of Teachers of Mathematics in April 2016.
The book is:
* Aimed at teachers of mathematics who are interested in addressing issues of social justice in their classrooms.
* Based on the premise that conventional approaches to teaching maths do not adequately address the needs of all learners or the needs of society as a whole.
* Suitable for students in Key Stages 3 and 4, those studying the new ‘core mathematics’ curriculum and for those on post-compulsory numeracy courses.
* Written in a style that allows teachers to use the ideas in a flexible, creative and non-prescriptive way.
The book contains:
* Seven projects addressing issues of social justice in the mathematics classroom;
* Twenty task sheets designed to be photocopied for students;
* Teachers’ notes offering ideas for supporting and developing classroom practice;
* Six accessible research articles exploring the theories underlying the teaching ideas.
Further details of the book can be found on:
and on the ATM website:
Dr Peter Gates
A UK university is giving its female professors a one-off salary hike to wipe out the gender pay gap with their male colleagues.
The University of Essex is raising female professors’ pay, to bring their average salaries level with the men.
It comes as UK pay data analysis by the Times Higher Education says full-time female academics are paid 11% less than men.
Essex said the move was motivated by “impatience” for change over the issue.
It is not just a step in right direction, it is a step that shows that other universities attempt to perform moonwalk on the issue.
The 13th International Conference of the Mathematics Education for the Future Project in Catania, Sicily September 2015, was attended by 130 people from 22 countries. The next conference will be held NEXT YEAR at Balatonfüred, Balaton lake, Hungary from September 10-15, 2017. The conference title, Mathematics Education for the next Decade, continues our search for innovation in mathematics, science, computing and statistics education. Our thirteen previous conferences since 1999 were renowned for their friendly and productive atmosphere, and attracted many /movers and shakers/ from around the world.
We now call for papers and workshop summaries for presentation at the conference and publication in the printed conference proceedings. For further details and updates please email alan >>at<< cdnalma.poznan.pl
The international conference on E-Assessment in Mathematical Sciences is a two-day academic conference organised by Newcastle University.
The conference aims to bring together researchers and practitioners with an interest in e-assessment for mathematics and the sciences. It will consist of a mix of presentations of new techniques, and pedagogic research, as well as workshops where you can get hands-on with leading e-assessment software.
The conference website is http://eams.ncl.ac.uk/.
The deadline for talk proposals is next Tuesday, the 31st of May (though that might be extended if we don’t get too many proposals in the next week), and the deadline for delegate registration is the 30th of June.
France DGSE: Spy service sets school code-breaking challenge
France’s external intelligence service, the DGSE, has sponsored a school competition to find the nation’s most talented young code-breakers.
It is the first time the DGSE has got involved in such a project in schools.
The first round drew in 18,000 pupils, and just 38 competed in the final on Wednesday, won by a Parisian team.
STEM Competitions Motivate Students :
“The main message is mathematics is not about numbers and figures,” [Mark] Saul said. “It’s about figuring things out. Whenever you’re figuring something out, you’re doing something mathematical.”
Rebecca Hanson Launches A Breakthrough in Maths Teaching for Primary Students :
Rebecca Hanson has opened her agency Authentic Maths to help Primary School Teachers in the UK offering solutions to the difficulties being experienced with the implementation of the Government’s changes to the primary mathematics curriculum.
UK follows Russia’s example to set up specialist sixth form maths colleges:
A key figure in the establishment of specialist maths institutions in the UK was Baroness (Alison) Wolf, a professor at King’s College London. She knew about Russian maths skills because of her work in universities, where maths departments often attract a fair few Russian academics.
Initially, the idea in the UK was for universities to set up a nationwide network of specialist maths schools. However, only King’s College London and Exeter have taken the plunge.