Derek M. Jones

Karma: 16

Derek M. Jones 13 Jan 2021 18:53 UTC
1 point
on: Any examples of people analyzing/critiquing scientific studies or papers?
You need to learn what to avoid: http://shape-of-code.coding-guidelines.com/2016/06/10/finding-the-gold-nugget-papers-in-software-engineering-research/
Andrew Gelman’s blog has lots of what you are after: https://statmodeling.stat.columbia.edu/

Derek M. Jones 4 Jan 2021 15:09 UTC
2 points
on: What technical-ish books do you recommend that are readable on Kindle?
If you are into data analysis and software engineering there is my book Evidence-based software engineering.
pdf+data+code here: http://knosof.co.uk/ESEUR/

Derek M. Jones 14 Aug 2020 17:49 UTC
2 points
on: Room and Board for People Self-Learning ML or Doing Independent ML Research
I wish you lots of luck. Don’t go so far north that day trippers from the south cannot drop by :-)
http://shape-of-code.coding-guidelines.com/2017/03/31/gentleman-scientists-in-software-engineering/

Derek M. Jones 21 Jun 2020 16:18 UTC
2 points
on: My weekly review habit
You are one of the few people with the discipline to record what they do and create todo lists. I could not keep this up for a week. Do you try to estimate the time it will take to complete a task?
Have you done any global analysis of your data? I analyse software engineering data and am always on the lookout for more data. I offer a free analysis, provided the data can be made public (in anonymous form). Here is one I did earlier:
http://shape-of-code.coding-guidelines.com/2019/12/15/the-renzo-pomodoro-dataset/

Derek M. Jones 6 May 2020 13:42 UTC
4 points
on: Maths writer/cowritter needed: how you can’t distinguish early exponential from early sigmoid
More examples of the difficulty of predicting the future using fitted regression models:
https://shape-of-code.coding-guidelines.com/2020/04/19/predicting-the-future-with-datalogistic-regression/

Derek M. Jones 14 Apr 2020 20:46 UTC
5 points
on: Is this viable physics?
Take some interesting ideas that allow larger structures to be built up, run an awful lot of computer simulations, and then have somebody who knows a huge amount about physics look for those outputs that match how parts of the universe have been previously modeled (with some success).
Where are the predictions? There are no predictions about basic stuff we know, like the electron orbitals of a Hydrogen atom, let alone predictions about stuff we don’t know.
This work looks interesting, and Wolfram is a great story teller. I hope something comes of it, but at the moment it is pure arm waving of just-so stories found in the output from a few computer runs.

Derek M. Jones 14 Apr 2020 12:43 UTC
3 points
on: Scraping websites currently free due to coronavirus
The ACM is offering free download of their articles: https://dl.acm.org/

Derek M. Jones 4 Apr 2020 20:50 UTC
5 points
on: Which books provide a good overview of modern human prehistory?
“Who we are and how we got here” by David Reich (a genetics professor who is a big name in the field), is the story of the various migrations and interbreeding of ‘human-like’ and human peoples over the last 50,000 years (with some references going as far back as 300,000 years).