Choose Language Hide Translation Bar
Community Trekker

parameter estimation in nonlinear platform

I want to use the nonlinear platform to estimate a parameter (2 actually) in a model.  I know how to do this in straightforward models.  The twist here is that I want this parameter to influence two columns with formulas - one column is used as an input to another, but the parameters are used in both columns.  Is there a way to optimize the parameters taking into account that they influence two different predictor expressions (one is an input to the other)?  Unfortunately, when I define a parameter to use in one predictor column, it is not available to use the same parameter in another column - it looks like I would need to define a different parameter in each column and then only optimize using one predictor column rather than have it affect both simultaneously.


Help will be appreciated.


Re: parameter estimation in nonlinear platform

Sorry, I don't have a solution but I think that it would be worth looking at Structural Equation Modeling (SEM) in JMP Pro 15. SEM is the only framework (as far as I am aware) that allows variables to be simultaneously inputs and outputs.

0 Kudos