Common Language Effect Size
Examples of ZumaStat Programs

Expands the Capabilities of SPSS and Excel 

Uses Summary Statistics as Input


ZumaStat
SPSS Interface
Means and ANOVA
Regression
Frequencies
Miscellaneous Utilties
Robust Statistics
Sample Programs
List of Programs
Support
Contact Us
Purchase
Disclaimers

 

 

Program Dynamic

There are many different indices of effect size.  A useful one that is easy for many people to understand is the Common Language Effect Size (CLES).  As applied to the analysis of means in two groups, the CLES tells you the probability that a randomly selected individual from one group will have a higher score on some variable than a randomly selected individual from another group.

For example, if the outcome variable is height, if you randomly select a male (Group 1) and a female (Group 2), what is the probability that the male will be taller than the female?  Or, what is the probability that a student randomly selected from a public school will have a higher reading score on a test than a student randomly selected from a private school?   

ZumaStat converts the CLES to an odds, which some find even more intuitive.

In the example below, the user enters the mean and standard deviation of the outcome variable for each group.  ZumaStat then tells you the odds that a person randomly selected from one group would have a higher score than an individual randomly selected from the other group.  The approach assumes scores are normally distributed and has reasonable robustness.  ZumaStat offers a nonparametric version of CLES as well.  The example shows how the dialog box looks after the data have been entered and the Calculate button is pressed. 

 

How it Appears on Your Screen