[Mu] [Delta] EPOW 15.369 3.639 WPOW 13.349 3.503 RPOW 13.518 3.721 LPOW 11.826 3.081 CPOW 3.275 3.225 MPOW 14.501 6.209 SPOW 15.523 6.166 SSAT 16.302 4.041 Table I.
The regression results indicate that both MPOW and SPOW are significant to the model with p-values of 0.001.
To determine if MPOW adds any predictive ability to the model, a lack of fit test was conducted using the full model above and a reduced model that dropped MPOW.
Again, the model requires both MPOW and SPOW; SPOW adds a considerable amount of predictive ability.
Further, we note that the coefficient for MPOW was also significant, suggesting that the model that best fits our data is one in which both variables are represented.
Although quite low, the reduced model using only SPOW had a higher [R.sup.2] than the reduced model using only MPOW. Both F-tests concluded that the full model, using both SPOW and MPOW, was a better model.
There is not enough evidence to support using the reduced model instead of the full model, indicating that the model requires both MPOW and SPOW.