Lack of fit in rsm

I am using response surface analysis with four factors using box behnken design but the lack of fit test is becoming significant.
Response: Cognitive_Demand
Df Sum Sq Mean Sq F value Pr(>F)
FO(x1, x2, x3, x4) 4 0.198030 0.049508 2.1970e+03 6.208e-07
TWI(x1, x2, x3, x4) 6 0.012877 0.002146 9.5245e+01 0.0002872
PQ(x1, x2, x3, x4) 4 0.002209 0.000552 2.4508e+01 0.0044902
Residuals 4 0.000090 0.000023
Lack of fit 1 0.000090 0.000090 4.6801e+29 < 2.2e-16
Pure error 3 0.000000 0.000000
How can I address this issue? how to solve the problem

Hi, can you provide a reproducible example?

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.