Spreadsheet Fever: It Is Easy to Catch
August 9, 2021
Regression is useful. I regress to my mean with every tick of my bio clock. I read “A Simple Regression Problem.” I like these explainer type of articles.
This write up contains a paragraph amplifying model fitting techniques, and I found this passage thought provoking. Here it is:
If you use Excel, you can try various types of trend lines to approximate the blue curve, and even compute the regression coefficients and the R-squared for each tested model. You will find very quickly that the power trend line is the best model by far, that is, An is very well approximated (for large values of n) by An = b n^c. Here n^c stands for n at power c; also, b and c are the regression coefficients. In other words, log An = log b + c log n (approximately).
The bold face indicates the words and phrases I found suggestive. With this encouraged twiddling, one can get a sense of how fancy match can be converted into a nifty array of numbers which flow. Even better, a graphic can be generated with a click.
What happens when data scientists and algorithm craftspeople assemble their confection of dozens, even hundreds, of similar procedures. Do you talk about Bayesian drift at the golf club? If yes, then toss in spreadsheet fever’s warning signs.
Stephen E Arnold, August 9, 2021
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
