Support parameter bounds on Fit CurveParameter Bounds on Fit Curve (similar to Parameter Bounds that can be estimated in classic Nonlinear)
mjoner
Re: Support parameter bounds on Fit Curve - Status changed to: Not Planned For NowHi, @mjoner Here is the workaround for this with non-linear. From development, it sounds like this is not a priority as we have a workaround.
After fitting a model in Fit Curve, you can choose "Save Parametric Prediction
Formula". This saves the prediction formula in a way that can be easily used by
the classic Nonlinear platform. So if you relaunch Nonlinear and use the new
parametric prediction formula, you can use the classic nonlinear platform to do
fine-tuning like setting parameter bounds, convergence criteria, and so on.
Re: Support parameter bounds on Fit Curve - Status changed to: Open for VotingRe: Support parameter bounds on Fit Curve<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />This is a useful workaround. I should have thought of that. Thanks.
Re: Support parameter bounds on Fit CurveComment from one of our developers:
This is definitely something that we should consider adding in the future. But in the meantime, there is a workaround that may help some users...
After fitting a model in Fit Curve, you can choose "Save Parametric Prediction Formula". This saves the prediction formula in a way that can be easily used by the classic Nonlinear platform. So if you relaunch Nonlinear and use the new parametric prediction formula, you can use the classic nonlinear platform to do fine-tuning like setting parameter bounds, convergence criteria, and so on.
Definitely not an ideal solution, but it may be helpful until we are able to make changes in Fit Curve.
cc:mjoner
