My Math Forum  

Go Back   My Math Forum > High School Math Forum > Probability and Statistics

Probability and Statistics Basic Probability and Statistics Math Forum


Reply
 
LinkBack Thread Tools Display Modes
November 7th, 2016, 02:45 AM   #1
Newbie
 
Joined: Mar 2016
From: Alabama

Posts: 18
Thanks: 0

Effect size for t-test

I downloaded some sample data from Wikipedia and tried some statistical analysis in R: https://drive.google.com/open?id=0B9...jJGX0RoOTRpWUU (https://drive.google.com/open?id=0B9...jVxbDljZ0FvUmc)

But I have a question. On this page: Quick-R: Power Analysis it says "Cohen suggests that d values of 0.2, 0.5, and 0.8 represent small, medium, and large effect sizes respectively." It gives a formula for d as absolute value of difference in means by square root of common error variance. On this page: https://onlinecourses.science.psu.edu/stat501/node/254 it says common error variance is estimated as mean square error on linear regression. However, using the root mean square approach used in this page: https://heuristically.wordpress.com/...-in-r-and-sas/ gives effect sizes of more than 1.

Where did I go wrong? I would also appreciate having other mistakes pointed out.
zambod is offline  
 
Reply

  My Math Forum > High School Math Forum > Probability and Statistics

Tags
effect, size, ttest



Thread Tools
Display Modes


Similar Threads
Thread Thread Starter Forum Replies Last Post
axiomatic descriptions of even size or odd size Soul Elementary Math 3 March 24th, 2016 02:41 PM
Set size is relative - Same topology of negative size sets BenFRayfield Applied Math 4 December 21st, 2013 10:58 PM
bernoulli effect Kinroh Physics 1 October 28th, 2013 03:43 PM
income effect pomazebog Economics 1 August 12th, 2012 10:55 PM
Substitution Effect pomazebog Economics 2 May 22nd, 2012 08:30 PM





Copyright © 2019 My Math Forum. All rights reserved.