Straightforward explanation of Theil inequality statistic for curve fitting

by Will   Last Updated July 12, 2019 09:19 AM - source

I’ve come across a paper (here) that uses a “Thiel inequality statistic” (pages 9 and 10 of the supplementary information) to determine goodness of fit for a model with its training data. I was wondering if you might be able to point me towards a straightforward explanation of how it works, and how it could be used in this context?

They also use a simple root-mean square error, does the Thiel statistic add anything that RMSE doesn’t?

I'm sorry if this is a lame question, please do let me know if you need any other information for it to make sense.



Related Questions



Fitting a dose response curve to 3 dose points

Updated May 15, 2017 14:19 PM



Maximum Likelihood Curve/Model Fitting in Python

Updated May 15, 2017 14:19 PM