StatsBlogs

The Map Is Not The Territory

Phil — Wed, 02 Oct 2019 06:04:57 +0000

This post is by Phil Price, not Andrew. My wife and I are building a new house, or, rather, paying trained professionals to build one for us. We are trying to make the house as environmentally benign as we reasonably can: ducted mini-split heating, heat pump water heater, solar panels, heat-recovery ventilator, sustainably harvested lumber, […]

The post The Map Is Not The Territory appeared first on StatsBlogs.

Total curvature of a knot

John — Wed, 02 Oct 2019 04:18:10 +0000

Tie a knot in a rope and join the ends together. At each point in the rope, compute the curvature, i.e. how much the rope bends, and integrate this over the length of the rope. The Fary-Milnor theorem says the result must be greater than 4π. This post will illustrate this theorem by computing numerically […]

The post Total curvature of a knot appeared first on StatsBlogs.

Prairie chair

xi'an — Tue, 01 Oct 2019 22:19:11 +0000

Today is the launching day of PRAIRIE, one of the four Instituts Interdisciplinaires d’Intelligence Artificielle (3IA) supported by the French government. Taking place in Paris Dauphine, with Yann Le Cun as guest speaker. I have been fortunate to be endowed with one of these chairs for the coming years, along with my CEREMADE colleagues Laurent […]

The post Prairie chair appeared first on StatsBlogs.

New vtreat Documentation (Starting with Multinomial Classification)

John Mount — Tue, 01 Oct 2019 19:08:30 +0000

Nina Zumel finished some great new documentation showing how to use Python vtreat to prepare data for multinomial classification mode. And I have finally finished porting the documentation to R vtreat. So we now have good introductions on how to use vtreat to prepare data for the common tasks of: Regression: R regression example, Python … Continue reading New vtreat Documentation (Starting with Multinomial Classification)

The post New vtreat Documentation (Starting with Multinomial Classification) appeared first on StatsBlogs.

“Less Wow and More How in Social Psychology”

Andrew — Tue, 01 Oct 2019 13:23:38 +0000

Fritz Strack sends along this article from 2012 which has an interesting perspective. Strack’s article begins: But, he continues, things changed in 2011 with the scandals of Diederik Stapel (a career built upon fake data), Daryl Bem (joke science getting published in a real journal), and a seemingly unending series of prominent studies that failed […]

The post “Less Wow and More How in Social Psychology” appeared first on StatsBlogs.

if you are looking for me today…

xi'an — Tue, 01 Oct 2019 08:01:46 +0000

The post if you are looking for me today… appeared first on StatsBlogs.

That study about the health risks of red meat: An excellent news report

Andrew — Tue, 01 Oct 2019 01:54:21 +0000

A couple different people pointed me to this excellent news article by Gina Kolata (with Brad Plumer), who writes: Public health officials for years have urged Americans to limit consumption of red meat and processed meats because of concerns that these foods are linked to heart disease, cancer and other ills. But on Monday, in […]

The post That study about the health risks of red meat: An excellent news report appeared first on StatsBlogs.

Nature snippets

xi'an — Mon, 30 Sep 2019 22:19:24 +0000

In the August 1 issue of Nature I took with me to Japan, there were many entries of interest. The first pages included a tribune (“personal take on events”) by a professor of oceanography calling for a stop to the construction of the TMT telescope on the Mauna Kea mountain. While I am totally ignorant […]

The post Nature snippets appeared first on StatsBlogs.

Many perspectives on Deborah Mayo’s “Statistical Inference as Severe Testing: How to Get Beyond the Statistics Wars”

Andrew — Mon, 30 Sep 2019 21:42:10 +0000

This is not new—these reviews appeared in slightly rawer form several months ago on the blog. After that, I reorganized the material slightly and sent to Harvard Data Science Review (motto: “A Microscopic, Telescopic, and Kaleidoscopic View of Data Science”) but unfortunately reached a reviewer who (a) didn’t like Mayo’s book, and (b) felt that […]

The post Many perspectives on Deborah Mayo’s “Statistical Inference as Severe Testing: How to Get Beyond the Statistics Wars” appeared first on StatsBlogs.

“Troubling Trends in Machine Learning Scholarship”

Andrew — Mon, 30 Sep 2019 13:49:05 +0000

Garuav Sood writes: You had expressed slight frustration with some ML/CS papers that read more like advertisements than anything else. The attached paper by Zachary Lipton and Jacob Steinhardt flags four reasonable concerns in modern ML papers: Recent progress in machine learning comes despite frequent departures from these ideals. In this paper, we focus on […]

The post “Troubling Trends in Machine Learning Scholarship” appeared first on StatsBlogs.

National Academies of Science: Please Correct Your Definitions of P-values

Mayo — Mon, 30 Sep 2019 05:46:28 +0000

If you were on a committee to highlight issues surrounding P-values and replication, what’s the first definition you would check? Yes, exactly. Apparently, when it came to the recently released National Academies of Science “Consensus Study” Reproducibility and Replicability in Science 2019, no one did. This Consensus Study was prompted by concerns about the reproducibility […]

The post National Academies of Science: Please Correct Your Definitions of P-values appeared first on StatsBlogs.

from here to infinity

xi'an — Sun, 29 Sep 2019 22:19:22 +0000

“Introducing a sparsity prior avoids overfitting the number of clusters not only for finite mixtures, but also (somewhat unexpectedly) for Dirichlet process mixtures which are known to overfit the number of clusters.” On my way back from Clermont-Ferrand, in an old train that reminded me of my previous ride on that line that took place […]

The post from here to infinity appeared first on StatsBlogs.

Convergence diagnostics for Markov chain simulation

Andrew — Sun, 29 Sep 2019 21:43:49 +0000

Pierre Jacob writes regarding convergence diagnostics for Markov chain simulation: I’ve implemented an example of TV upper bounds for (vanilla) HMC on a model written in Stan, see here and here for a self-contained R script. Basically, this creates a stan fit object to obtain a target’s pdf and gradient, and then implements a pure […]

The post Convergence diagnostics for Markov chain simulation appeared first on StatsBlogs.

A sort of mathematical quine

John — Sun, 29 Sep 2019 21:33:19 +0000

Julian Havil writes what I think of as serious recreational mathematics. His books are recreational in the sense that they tell a story rather than cover a subject. They are lighter reading than a text book, but require more advanced mathematics than books by Martin Gardner. Havil’s latest book is Curves for the Mathematically Curious. […]

The post A sort of mathematical quine appeared first on StatsBlogs.

Here’s a supercool controversy for ya

Andrew — Sun, 29 Sep 2019 13:22:02 +0000

Raghu Parthasarathy writes: You might like this very good article by Ashley Smart on a recent fight about the statistical mechanics of water, and a feud that was made worse by a lack of sharing code Condensed matter theory! That’s what I worked on, back when I was a physicist. We did an experiment that […]

The post Here’s a supercool controversy for ya appeared first on StatsBlogs.

Tidy forecasting in R

Hyndsight on Rob J Hyndman — Sun, 29 Sep 2019 00:00:00 +0000

The fable package for doing tidy forecasting in R is now on CRAN. Like tsibble and feasts, it is also part of the tidyverts family of packages for analysing, modelling and forecasting many related time series (stored as tsibbles).
For a brief introduct...

The post Tidy forecasting in R appeared first on StatsBlogs.

Antarctic sabbatical

xi'an — Sat, 28 Sep 2019 22:19:33 +0000

Airbnb is supporting 5 volunteers that wish to join next December environmental scientist Kirstie Jones-Williams, from the University of Exeter, on a scientific expedition in Antarctica, investigating the presence of microplastics there. The deadline for applications is 11:59pm EDT on 8 October 2019. (I wish I could, but the news came a bit late to […]

The post Antarctic sabbatical appeared first on StatsBlogs.

Control characters

John — Sat, 28 Sep 2019 14:53:05 +0000

I didn’t realize until recently that there’s a connection between the control key on a computer keyboard and controlling a mechanical device. Both uses of the word control are related via ASCII control characters as I discovered by reading the blog post Four Column ASCII. Computers work with bits in groups of eight, and there […]

The post Control characters appeared first on StatsBlogs.

Controversies in the theory of measurement in mathematical psychology

Andrew — Sat, 28 Sep 2019 13:56:26 +0000

We begin with this email from Guenter Trendler: On your blog you wrote: The replication crisis in social psychology (and science more generally) will not be solved by better statistics or by preregistered replications. It can only be solved by better measurement. Check this out: Measurement Theory, Psychology and the Revolution That Cannot Happen (pdf […]

The post Controversies in the theory of measurement in mathematical psychology appeared first on StatsBlogs.

Columbia statistics department hiring teachers and researchers

Andrew — Sat, 28 Sep 2019 00:29:31 +0000

Details here. Here are the four positions: 1. The Department of Statistics invites applications for a tenure-track Assistant Professor position to begin July 1, 2020. A Ph.D. in statistics or a related field is required. Candidates will be expected to sustain an active research and publication agenda and to teach in the departmental undergraduate and […]

The post Columbia statistics department hiring teachers and researchers appeared first on StatsBlogs.