What is the lack of fit test?

The lack-of-fit test assess the fit of your model. If the p-value is less than your selected a-level, evidence exists that your model does not accurately fit the data. You may need to change your model or transform your data to more accurately model the data.

Nonlinear regression uses the pure error lack of fit test. Minitab automatically displays this test if your data contain replicates (multiple observations with identical x-values). Different response values of replicates represent "pure error" because only random variation can cause differences between the observations for each replicate.