is there... an ... elegant, slim, mathematically robust HS level book on statistics?
This will sound a little gauche but most of the books just have way too many words and not enough content.
Math books should have paragraphs that take you like a hour to read, but not very many of them, and more equations IMO.
This book, it's just so... long winded.
@futurebird Good luck. I’ve been unhappy with how statistics gets taught since the eighties.
I mean... same but I've only been teaching for 25 years or so.
I love statistics so much... the real math part of it, but most class are like baking classes where you memorize unintelligible recipes... or it's just a bunch of reading that is somehow both dense and devoid of real content.
@futurebird @SistaWendy still sound better than my college stats class. Charts instead of math. High school was better. Though at the end of the day, isn't it just a few variations of the same formula?
@futurebird Let me stipulate that I have zero specific knowledge of teaching math.
But you seem to be saying that there’s only one valid way of teaching and learning math, and that makes me instinctively suspicious.
@futurebird One thing I suffered from at university (on an engineering course) was long explanations which went through every step of some process (deriving some formula, say) and got in the way of seeing how the process was meant to work and why—the detail got in the way of seeing the actual principles. It absolutely felt like following recipes without understanding why I'd want to treat a particular ingredient a particular way . . .
@futurebird I am not joking, i wholeheartedly recommend the Cartoon Guide to Statistics
Oct 31, 2026, 7:52 AMI can confirm that the above recommendation is not a joke. I was recommended this book almost 15 years ago and would recommend it to others.
@david_chisnall @ansate @futurebird In a similar vein, "how to lie with statistics" was the basic text for the intro course at UC Davis when I was there in the '80s, and everyone who took it raved. https://www.thriftbooks.com/w/how-to-lie-with-statistics_darrell-huff/253063/item/12982713/
Oct 31, 2026, 3:23 PM@ansate I recommend it as well. It's right on target for you @futurebird .
@futurebird I quite liked OpenIntro Statistics (free, but I ended up buying the book). I came to it as an old engineer trying to learn enough to follow data science conversations.
@futurebird hm, I seem to recall bstacey@icosahedron.website was building up a list of math and physics textbooks , but I think most were aimed at college students. Nonetheless - maybe they have some ideas.
@futurebird I don't have any specific recommendations, except to say that Dover Publications generally has good, economical math texts: https://store.doverpublications.com/collections/math-probability-and-statistics
Oct 31, 2026, 12:49 AMHm. I loved statistics class, BUT, as I recall, it was lecture- based, and lower division college. If there was a book, alas, I can't recall it.
I guess that was too long ago anyway, barely out of slide rule territory.
we should video chat probably because I have lots of thoughts on this...
At one level I want to say: perhaps Probability Theory The Logic of Science is really where everyone should start.
But from a practical perspective Statistical Rethinking by McElreath is what you get when McElreath reads PTTLOS and tries to teach that... so maybe start there...
Stats is not really a math course, and the most important components of statistics are really building models
@futurebird
is more about words you use to describe a scientific thing, and then converting those words to equations and incorporating uncertainty... and thats more words less theorems and equations.
@futurebird
Also I am firmly of the belief noone should learn frequentist statistics first. this is critical because it will absolutely damage your ability to do statistics if you do.
I think when teaching statistics, the first place to start is with a set of experiments you are going to run. Literal physical experiments. For example you could drop little paper helicopters with a paperclip and measure their flight time. You could drop balls of crumpled paper and measure their drop time. You could roll balls down ramps and measure the rolling time. You could measure the time to drain a funnel with different types of cooking oil, at different temperatures.
Whatever these experiments are, you should be talking about the instrumentation you're using to do the measurements, and the ways in which your measurements might not fully accurately reflect the reality of what happened.
I did an experiment where I took a plastic disposable pipette and dripped water onto a scale, and did so after cutting the pipette shorter and shorter and measuring the diameter of the opening each time... And my kids and I built a model of surface tension
So, this is why I say math is not really the key in a good stats textbook, because what really matters is thinking about connecting an experiment to a model, and you can do pretty easy models that require only basic algebra and things.
@dlakelan @futurebird hard agree
The surface tension model was great because most scales have a nonlinear behavior near zero! So now you're modeling both the droplet formation and the forces from surface adhesion, and the measurement scale and its nonlinearity for small mass/weight. It doesn't take more than algebra really but it does take thinking clearly about which particular algebra!
Oct 31, 2026, 7:39 AM100% agreed. I always found statistics to be a bunch of weird maths that did… something? But not for reasons anyone could explain to me, just memorise the formula.
Then someone explained to me that statistics is about determining the likelihood that a model corresponds to reality. So you need to have a model and you need to have some experiment, and you’re trying to make sure that the experiment samples enough of the space that each new sample can (ideally) eliminate some alternative models and give confidence to your model.
And, once I understood that, a bunch of statistical techniques made sense because they’re just trivial applications of probability. And those weird formulae are just reusable partial applications, like the quadratic equation formula that is just the result of completing the square on a quadratic where all of the variables are symbolic.
@david_chisnall
I love this so much. Yes, the formulas for quantiles of the standard normal and all that stuff is just that, formulas, by themselves they have no meaning, theyre just math facts like 2+2=4 but the whole point of statistics is "how well does this model correspond to reality?"
@futurebird
I'm getting that sinking feeling that the exact book I wish existed might still need to be written.
Oct 31, 2026, 11:27 AMGood news! There is a market opportunity for you!
@futurebird My favorite statistics book is Statistics for Physicists by BR Martin. Maybe not HS level but no more than college level. As the name hints, aimed toward statistical tests needed in experimental physics, but applicable to many things. worldcat.org can find you a copy.
@futurebird I quite liked “Fundamental Statistics for the Behavioural Sciences” (Howell).
@futurebird I had to be a temp teacher for HS level stats and I was horrified by the textbook. It didn't even properly explain what probability was and just jumped to normal distrubutions.
I was surprised when a CSIRO statistician recommended this one. He was spot on
https://www.larrygonick.com/titles/science/the-cartoon-guide-to-statistics/
@futurebird i just skimmed it more than a decade ago, but https://www.oreilly.com/library/view/statistics-in-a/9781449361129/ might be on the right level?
@psentee
"Access Denied" ?
What is the title?
@futurebird O’Reilly’s „Statistics in a Nutshell” by Sarah Boslaugh