Engineering Statistics Handbook (2012)

https://www.itl.nist.gov/div898/handbook/index.htm

by gballan • 3 years ago

186 24 3 years ago

itl.nist.gov

sieste• 3 years ago

Books like these should be read by all mathematics/statistics students, not to get better at mathematics, but to see how the concepts they study in theory are relevant in practice.

Koshkin• 3 years ago

Indeed, statistics (as opposed to probability theory) is more like physics, in its relation to mathematics.

GTP2• 3 years ago

Anyone used this in the past? Do you think it's a good book?

avs733• 3 years ago

It’s good. I provide it to students as a resource and bring it up on a couple of topics when I teach undergraduate engineers statistics

happy3483t5835• 3 years ago

It's good but it's old-school, focusing on traditional null hypothesis significance testing and related ideas. These ideas have been under attack for decades, most recently as being one cause of the scientific replicability problem.

If you're new to applied stats, be aware that there's a whole other world out there, beautifully taught to beginners by https://xcelab.net/rm/statistical-rethinking/

brennanpeterson• 3 years ago

It is old school in the sense that it is quite pragmatic. It is aimed at Mainstays of engineering like 'did I improve performance in this line' or 'ate these systems giving the same output's or even 'how do.i design an experiment in a really complex system'. And they generally work well.

Just do work using appropriate tools. There are reasons for all sorts of tools, use the right ones.

Reproducibility crisis is mostly about marginal results, publication bias, and humans.behavior. Bayesians can (and do!) The same things. It isn't the tool, it is the people.

mdp2021• 3 years ago

Excellent, Richard McElreath also publishes lectures full lectures at

https://www.youtube.com/@rmcelreath/videos

stiff• 3 years ago

The book has eight voluminous chapters and only one is about hypothesis testing. Much of it is about design of experiments and statistical process control, think something like optimizing the workings of a factory. Hypothesis testing has been under attack in psychology/economics/etc., as part of I think a broader problem those disciplines have drawing reliable conclusions in general, since it is difficult to control all the variables. This book is about engineering and industrial applications which are closer to physics.

hcks• 3 years ago

Any other recommendation with the same focus?

iancmceachern• 3 years ago

There is a book called "statistics for engineers and scientists "

ta_tunestub• 3 years ago

“The Book of Why” and “Statistical Rethinking” course [1]

[1]https://twitter.com/chrismgreer/status/1714687870286655885?s...

dpflan2• 3 years ago

Is there an updated version?

crispyambulance2• 3 years ago

It's maintained, minor changes as late as January 2023 (https://www.itl.nist.gov/div898/handbook/changes.htm).

This is stable stuff!

The retro html needs a bit of a refresh, but everything seems to work AFAIK.

dpflan2• 3 years ago

Thanks for pointing out the refresh.

boredemployee• 3 years ago

I read a few mins of the book and loved it, but I confess that the comments here have left me a bit confused.

I have a degree in engineering, took two statistics courses that basically used high school level math.

Nowadays, I work with data analysis, using SQL and Python. And I would like to know which statistical approach you guys think are most suitable for the real world, like how to test hypothesis etc?

brutusborn• 3 years ago

I think the examples in the handbook are excellent, as an engineer I started on the pipeline example [1]. In terms of testing hypothesis, the design of experiments section is useful [2].

[1] https://www.itl.nist.gov/div898/handbook/pmd/section6/pmd62.... [2] https://www.itl.nist.gov/div898/handbook/pmd/section3/pmd31.....

Engineering Statistics Handbook (2012)

Related Stories