cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Register for our Discovery Summit 2024 conference, Oct. 21-24, where you’ll learn, connect, and be inspired.
%3CLINGO-SUB%20id%3D%22lingo-sub-783398%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%C2%BFC%C3%B3mo%20obtengo%20el%20valor%20de%20R-Sq%2C%20L1%2C%20L2%20y%20lambda%20de%20la%20plataforma%20Elastic%20Net%20Regression%20para%20poder%20comparar%20modelos%3F%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-783398%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%3CP%3EEstoy%20comparando%20diferentes%20configuraciones%20de%20par%C3%A1metros%20para%20algunos%20modelos%20de%20regresi%C3%B3n%20de%20red%20el%C3%A1stica%20en%20un%20conjunto%20de%20datos%20peque%C3%B1o%20para%20demostrar%20en%20qu%C3%A9%20punto%20los%20conjuntos%20de%20datos%20son%20demasiado%20peque%C3%B1os%20para%20los%20m%C3%A9todos%20de%20regresi%C3%B3n%20y%20quiero%20comparar%20entre%20JMP%2C%20SAS%2C%20R%20y%20Python.%20Aunque%20puedo%20configurar%20el%20alfa%2C%20no%20puedo%20ver%20c%C3%B3mo%20generar%20directamente%20los%20valores%20lambda%2C%20L1%20y%20L2%20que%20se%20usan%20en%20los%20modelos%20elegidos%20y%20el%20R-Sq%20resultante%20para%20el%20modelo.%20%C2%BFHay%20un%20clic%20derecho%20secreto%20en%20alg%C3%BAn%20lugar%20que%20me%20estoy%20perdiendo%2C%20ya%20que%20hubiera%20pensado%20que%20estas%20son%20cosas%20bastante%20sencillas%20que%20la%20gente%20quiere%20ver%3F%20Y%20el%20otro%20software%20parece%20darlos%20de%20diferentes%20maneras.%3C%2FP%3E%3CP%3EEstoy%20usando%20JMP%20Po%2018%20y%20usando%20el%20m%C3%A9todo%20de%20validaci%C3%B3n%20cruzada%20Leave%20one%20out%2C%20lo%20que%20tambi%C3%A9n%20parece%20significar%20que%20no%20se%20generan%20estad%C3%ADsticas%20de%20resumen%20de%20comparaci%C3%B3n%20de%20modelos%20(s%C3%AD%20si%20elijo%20AICc%20o%20BIC%20como%20m%C3%A9todo%20CV)...%20%C2%BFes%20correcto%3F%3C%2FP%3E%3CP%3EGracias%20de%20antemano.%3C%2FP%3E%3C%2FLINGO-BODY%3E%3CLINGO-LABS%20id%3D%22lingo-labs-783398%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%3CLINGO-LABEL%3EModelado%20estad%C3%ADstico%20avanzado%3C%2FLINGO-LABEL%3E%3C%2FLINGO-LABS%3E%3CLINGO-SUB%20id%3D%22lingo-sub-783411%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3ERe%3A%20%C2%BFC%C3%B3mo%20obtengo%20el%20valor%20de%20R-Sq%2C%20L1%2C%20L2%20y%20lambda%20de%20la%20plataforma%20Elastic%20Net%20Regression%20para%20poder%20comparar%20modelos%3F%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-783411%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%3CP%3EPuede%20extraer%20estos%20valores%20de%20forma%20interactiva%20haciendo%20clic%20derecho%20en%20la%20columna%20de%20n%C3%BAmeros%20y%20seleccionando%20Convertir%20en%20tabla%20de%20datos.%20Puede%20crear%20un%20script%20para%20esta%20acci%C3%B3n%20o%20una%20extracci%C3%B3n%20m%C3%A1s%20espec%C3%ADfica.%3C%2FP%3E%3C%2FLINGO-BODY%3E%3CLINGO-SUB%20id%3D%22lingo-sub-783602%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3ERe%3A%20%C2%BFC%C3%B3mo%20obtengo%20el%20valor%20de%20R-Sq%2C%20L1%2C%20L2%20y%20lambda%20de%20la%20plataforma%20Elastic%20Net%20Regression%20para%20poder%20comparar%20modelos%3F%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-783602%22%20slang%3D%22en-US%22%20mode%3D%22CREATE%22%3E%3CP%3EGracias%20por%20esto%2C%20Mark%2C%20pero%20ni%20siquiera%20puedo%20encontrar%20los%20valores%20en%20la%20salida%20para%20poder%20hacer%20eso.%20Una%20respuesta%20de%20un%20t%C3%A9cnico%20de%20JMP%20dec%C3%ADa%20%22no%20muestran%20estos%20valores%22%2C%20lo%20cual%20me%20resulta%20un%20poco%20dif%C3%ADcil%20de%20entender%2C%20ya%20que%20seguramente%20uno%20quiere%20poder%20ver%20lambda%2C%20L1%20y%20L2%2C%20como%20m%C3%ADnimo.%20%C2%BFA%20menos%20que%20se%20les%20llame%20con%20un%20nombre%20diferente%20en%20la%20salida%20de%20JMP%3F%3C%2FP%3E%3CP%3ETambi%C3%A9n%20dijeron%20que%20no%20se%20obtiene%20un%20R-Sq%20si%20se%20usa%20K-Fold%20o%20LOO%20como%20validaci%C3%B3n%2C%20pero%20no%20hay%20ninguna%20explicaci%C3%B3n%20de%20por%20qu%C3%A9%20no.%20%C2%BFAlguna%20idea%3F%20Estoy%20bastante%20seguro%20de%20que%20SAS%20los%20proporciona%20directamente%2C%20as%C3%AD%20que%20no%20estoy%20seguro%20de%20por%20qu%C3%A9%20JMP%20no%20lo%20hace.%3C%2FP%3E%3C%2FLINGO-BODY%3E
Choose Language Hide Translation Bar
gemmahodgson
Level III

How do I get the value of the R-Sq, L1, L2 and lambda out of Elastic Net Regression platform so I can compare models?

I am comparing different parameter settings for some elastic net regression models on a smallish data set to demonstrate at what point datasets are too small for regression methods and want to compare between JMP, SAS, R and Python. Although I can set the alpha, I can't see how to directly output the lambda, L1 and L2 values that are used in the chosen models and the resulting R-Sq for the model. Is there a secret right click somewhere I'm missing as I would've thought these are pretty straightforward things that people want to see? And the other software seem to give these in varying ways.

I am using JMP Po 18 and using the Leave one out cross validation method - which also seems to mean no model comparison summary statistics are generated (they are if I choose AICc or BIC as the CV method)...is that right?

Thanks in advance.

2 REPLIES 2

Re: How do I get the value of the R-Sq, L1, L2 and lambda out of Elastic Net Regression platform so I can compare models?

You can interactively extract these values by right-clicking on the column of numbers and selecting Make Into Data Table. You can script this action or a more specific extraction.

gemmahodgson
Level III

Re: How do I get the value of the R-Sq, L1, L2 and lambda out of Elastic Net Regression platform so I can compare models?

Thanks for this Mark, but I can't even find the values in the output to be able to do that. A reply from a JMP technician said "they don't surface these values", which I find a bit hard to understand as surely one wants to be able to see the lambda, L1 and L2 at the very least. Unless they are called by a different name in the JMP output?

They also said you don't get an R-Sq if you use K-Fold or LOO as validation - but no explanation as to why not - any ideas? I'm pretty sure SAS gives these directly so I'm not sure why JMP is not doing it?