Top all-time · #4793
the refsmmat report
Personal blog · refsmmat.com/posts · on HN as capnrefsmmatdatascience
the refsmmat report is a personal blog at refsmmat.com about data and science. Since 2012, 16 different Hacker News readers have linked it 45 times, most often “The history of “How to Lie with Smoking Statistics” (2014)”. The last post was in 2023, but the archive is still widely read.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
Linked as a reference on statistics, p-values, Simpson's paradox, smoking statistics and physics-and-pseudoscience topics. Commenters cite posts as sources; none judges the writing itself.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- The history of “How to Lie with Smoking Statistics” (2014)4 people · 5 mentions · first linked 2019-01-31
- Statistics Done Wrong: Inferential statistics and how scientists screw it up3 people · 5 mentions · first linked 2012-07-30
- The Unreasonable Ineffectiveness of Mathematics Education2 people · 2 mentions · first linked 2012-10-21
What Hacker News says?
Those interested in How to Lie with Statistics may also enjoy Huff's other book, How to Lie with Smoking Statistics , commissioned by the tobacco industry in the 60s to fight the growing evidence that smoking causes cancer. It was never published, but I compiled the surviving manuscript and wrote about it: https://www.refsmmat.com/articles/smoking-statistics.html
Comment linking /articles/smoking-statistics.html
on “Statistics Done Wrong”Submitted Statistics Done Wrong – The woefully complete guide as a story · 331 points
HN discussionI'm writing a book about the many ways well-intentioned scientists can (and usually do) screw up statistics: http://www.refsmmat.com/statistics/ I started when I was an undergraduate physics major. My entire statistics education consisted of thirty minutes being told not to use R^2. I started reading about statistical abuses and realized that I would probably have committed most of them had I published research -- m…
Comment linking /statistics/
on “Ask HN: What are you working on and why is it cool?”Submitted The history of “How to Lie with Smoking Statistics” (2014) as a story · 85 points
HN discussionIe. https://www.refsmmat.com/posts/2016-05-08-simpsons-paradox-b...
Comment linking /posts/2016-05-08-simpsons-paradox-berkeley.html
on “Simpson’s Paradox (2016)”Submitted The Unreasonable Ineffectiveness of Mathematics Education as a story · 79 points
HN discussionStandard teaching methods for science and math don't work by many measures. That's not the fault of poor teachers; even well-rated teachers do poorly at improving student understanding. This is largely the fault of our notion that teachers are explanation delivery devices and students explanation receptacles, where the only improvements can be found in better explanations and better student engagement. The notion is…
Comment linking /articles/shutup.html
on “North Carolina teacher's resignation letter”Submitted Some Ideas of Interactive Textbooks as a story · 6 points
HN discussionOne of the best articles covering this issues is Meehl[1][2]. You can find discussion in various places like Gelman[3] and Reinhart[4]. [1] Meehl, Paul E (1990). Why summaries of research on psychological theories are often uninterpretable. Psychological Reports, 66(1), 195–244. [2] http://meehl.umn.edu/files/144whysummariespdf [3] http://andrewgelman.com/2015/03/23/paul-meehl-continues-boss... [4] https://www.refsm…
Comment linking /notebooks/meehl.html
on “Why I've lost faith in p values”Submitted Statistics Done Wrong: Inferential statistics and how scientists screw it up as a story · 5 points
HN discussionI have the same fear of forgetting things and the desire to remember everything I've learned. I'm an academic, so mostly this means references to papers and books I've read, along with notes summarizing their contents. (My PhD advisor used to say that a sign of learning isn't whether you remember something -- it's how quickly you can re-learn it. So I try to make it easy to find and re-learn things I need.) Since I…
Comment linking /notebooks/
on “Tiddlywiki – A non-linear personal web notebook”Submitted The Unreasonable Ineffectiveness of Mathematics Education (2012) as a story · 4 points
HN discussionImagine testing 1000 potential cancer drugs. Only 100 of them actually work, but you don't know that; you have to do the trial. So you get out some petri dishes and start testing. You look for a 5% chance of false positive (p < 0.05), which is the statistical significance level usually used in medical trials. Of the 100 real drugs, you detect all of them. Of the 900 fake drugs, 5% of them falsely appear to work. So…
Comment linking /statistics/
on “Live CERN Higgs Announcement in 20 Mins ”Submitted Review: Neil Postman's 'Amusing Ourselves to Death' (2016) as a story · 3 points
HN discussionThe more important difference between mathematics education in Japan and mathematics education in (say) the United States is how hard the problems are and the encouragement to pupils in Japan to try to figure things out for themselves. I put instructional methodologies to the test by teaching supplemental mathematics courses to elementary-age pupils willing to take on a prealgebra-level course at that age. My pupils…
Comment linking /articles/unreasonable-math.html
on “How Japanese Kids Learn To Multiply”Submitted Where are the interactive textbooks? as a story · 3 points
HN discussionI am sometimes amused to read failed replication studies which do not calculate their own statistical power -- so they do not know whether, assuming the original study was correct, they will have the sample size to reliably detect an effect. A failed replication then says nothing about the original conclusions. Statistical error is a hobby of mine. The Economist mentions a few pervasive errors, but there are many mo…
Comment linking /statistics/p-value.html
on “To an alarming degree, science is not self-correcting”Submitted Statistics Done Wrong as a story · 3 points
HN discussionHTLwS was written as tobacco-lobby propaganda. < https://www.refsmmat.com/articles/smoking-statistics.html >
Comment linking /articles/smoking-statistics.html
on “Most books don't sell only a dozen copies”Submitted "How to Lie with Smoking Statistics" (2014) as a story · 2 points
HN discussionI've been co-teaching a class in computing for statisticians this semester (some details on the previous iteration here https://www.refsmmat.com/posts/2016-01-22-stat-computing.htm... ) and have mixed feelings about RStudio. Most of our students use RStudio for their work. It's convenient and easy. For developing standalone scripts or functions, rather than notebooks or R Markdown files, the typical workflow is to w…
Comment linking /posts/2016-01-22-stat-computing.html
on “Announcing RStudio v1.0”Submitted Statistical Programming Languages as a story · 2 points
HN discussionMy favorite term for that behavior is "stargazing," because they're staring at the little asterisks instead of thinking about the meaning of the results. I have been working on a guide for practicing scientists which attacks common statistical misconceptions: http://www.refsmmat.com/statistics/ It's on its way to publication, so you'll be able to hit your biologists upside the head with it in due time. (Although it'…
Comment linking /statistics/
on “P values are not as reliable as many scientists assume”Submitted R's Lists and Its Detestable Dearth of Data-Structures as a story · 2 points
HN discussionThis one in particular is quite good: http://www.feynmanlectures.caltech.edu/I_06.html Further study: http://www.refsmmat.com/statistics/
Comment linking /statistics/
on “The Feynman Lectures on Physics, Volume II”Submitted Statistics Done Wrong as a story · 2 points
HN discussionThere are many choices to make when statistically analyzing the data, and it is not terribly hard to play around with choices until you get a favorable result. For example, one common problem is truth inflation: clinical trials are conducted with too-small sample sizes, so they can't detect the result they're looking for. If you run enough of these, the only statistically significant results you will get will signif…
Comment linking /articles/statistics.html
on “The Deadly Corruption of Clinical Trials”Submitted "How to Lie with Smoking Statistics" as a story · 1 points
HN discussionI keep a notebook with a list of references on pedagogy, including active learning: https://www.refsmmat.com/notebooks/pedagogy.html The Peer Instruction section features a great deal of research in introductory physics courses, where well-implemented active learning methods can double or triple student learning of core concepts. (I also blogged about this research long ago: https://www.refsmmat.com/posts/2012-10-19…
Comment linking /posts/2012-10-19-shutup.html
on “Vermont Medical School Says Goodbye to Lectures”Submitted Shut Up and Listen to Your Students as a story · 1 points
HN discussion
