The coefficient of determination, corrected for the number of terms in the regression equation. It is typically lower and more stable than R-squared when the number of regression terms is varied.
R2Corrected= 1 - c ( 1 - R2 )
c = ( n - 1 ) / ( n - p - 1 )
n = number of runs; p = number of parameters estimated by regression
Learn more about the Regression tools in Six Sigma Demystified (2011, McGraw-Hill) by Paul Keller, in his online Regression short course (only $99), or his online Black Belt certification training course ($875).