Standard error of the estimate vs RMSE?

Discuss statistics related things

by cperdue » Thu Jun 11, 2020 8:38 pm

I'm currently using jamovi in my undergraduate statistics courses, and it appears to be a good fit so far. One thing I was curious about, though... in most of the undergraduate stat textbooks in the social sciences, the prediction error in regression is usually discussed in terms of the df-adjusted standard error of the estimate. I notice that jamovi reports the unadjusted root mean square error (RMSE) instead. Are their any plans to have jamovi report the standard error of the estimate in the regression output? It would be useful for instructional purposes ...
Posts: 5
Joined: Wed Oct 16, 2019 5:41 pm

by Ravi » Fri Jun 12, 2020 7:59 am

So I assume in terms of R output you mean the residual standard error?

Screenshot 2020-06-12 at 09.58.38.png
Screenshot 2020-06-12 at 09.58.38.png (84.71 KiB) Viewed 1368 times

If so, I can easily add that. Can you make an issue on our github so I won't forget:
User avatar
Posts: 162
Joined: Sat Jan 28, 2017 11:18 am

by gasper » Wed Dec 02, 2020 7:13 am

This will be a nice feature - you keep telling students that their predictions are not without error but if they can't calculate it, you can't test if they really understand it.

Thank you in advance.
Everything starts somewhere, although many physicists disagree. TP
Posts: 10
Joined: Tue Oct 13, 2020 8:27 am
Location: Slovenia

Return to Statistics