"Don't fit"

This checklist is for when the nonlinear regression process never started, and instead reports "Don't fit" at the top of the results. View other checklists if your curve fit ended with a different completion code: Completed, Bad initial values, Interrupted, Not converged, ambiguous, Hit constraint, Too few points, Perfect Fit or Impossible weights.

The top of the Diagnostics tab offers the choice to plot the curve defined by the initial values of the parameters.

When you make this choice, the top of the results will show "Don't fit".

This is a very useful option to use when diagnosing problem fits. But you won't learn anything by looking at the results page. Instead, look at the graph. If the curve goes near the points, then the initial values are OK. If the curve is far from the points, or follows a different shape altogether, then you know that there is a problem with the choice of model or initial values.

If you checked this option by mistake, go back to the Diagnostics tab and check the alternative choice ("Fit the curve.").