Effect size in multiple regression

  • Context: Undergrad 
  • Thread starter Thread starter bradyj7
  • Start date Start date
  • Tags Tags
    Multiple Regression
Join the discussion
Registration is free. Ask a follow-up in this thread, or start your own.
1 reply · 2K views
bradyj7
Messages
117
Reaction score
0
Hello,

I'm using this this calculator to determine a rough sample size for a multiple regression (20 predictors).

http://www.stattools.net/SSizmreg_Pgm.php

I don't really understand the effect size?

Could somebody tell me if you are using multiple regression (with 20 predictors) and you want the regression to have an R2 > 0.8, do you want a small effect size for example 0.2 or a large effect size for example 0.5?

Basically I want a accurate model, what effect size value should I use?

Thank you
 
Physics news on Phys.org