cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
%3CLINGO-SUB%20id%3D%22lingo-sub-249081%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3EAm%C3%A9liorer%20les%20tests%20d'%C3%A9quivalence%20dans%20Fit%20Y%20by%20X%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-249081%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CP%3ELa%20suggestion%20serait%20de%20permettre%20une%20r%C3%A9solution%20automatique%20de%20la%20valeur%20de%20diff%C3%A9rence%20qui%20donne%20l'%C3%A9quivalence%20pour%20un%20alpha%20donn%C3%A9.%3C%2FP%3E%3CP%3EDans%20l'exemple%3CA%20href%3D%22https%3A%2F%2Fwww.jmp.com%2Fsupport%2Fhelp%2Fen%2F15.0%2Fjmp%2Fexample-of-an-equivalence-test.shtml%23%22%20target%3D%22_self%22%20rel%3D%22noopener%20noreferrer%22%3E%20exemple-de-test-d'equivalence%3C%2FA%3E%20il%20y%20aurait%20une%20option%20%C3%A0%20r%C3%A9soudre%20pour%20la%20valeur%20de%20diff%C3%A9rence%20qui%20pr%C3%A9dit%20l'%C3%A9quivalence%20pour%20une%20valeur%20alpha%20donn%C3%A9e%20(en%20plus%20de%20l'option%20actuelle%20pour%20fournir%20une%20diff%C3%A9rence%20sp%C3%A9cifique).%20Souvent%2C%20cette%20valeur%20de%20diff%C3%A9rence%20est%20sp%C3%A9cifi%C3%A9e%20de%20mani%C3%A8re%20incoh%C3%A9rente%20au%20sein%20d'un%20d%C3%A9partement%20ou%20d'un%20groupe%20fonctionnel%20donn%C3%A9%20(souvent%20avec%20de%20nombreuses%20opinions%20divergentes).Ainsi%2C%20au%20lieu%20d'ex%C3%A9cuter%20plusieurs%20diff%C3%A9rences%20pour%20montrer%20les%20valeurs%20de%20p%20pour%20l'%C3%A9quivalence%2C%20il%20serait%3CEM%3E%3CSTRONG%3E%20tr%C3%A8s%3C%2FSTRONG%3E%3C%2FEM%3E%20pratique%20%C3%A0%20r%C3%A9soudre%20pour%20la%20diff%C3%A9rence%20qui%20pr%C3%A9dirait%20l'%C3%A9quivalence%20%C3%A9tant%20donn%C3%A9%20une%20valeur%20alpha.%3C%2FP%3E%3C%2FLINGO-BODY%3E%3CLINGO-LABS%20id%3D%22lingo-labs-249081%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CLINGO-LABEL%3EStatistiques%20et%20analyses%3C%2FLINGO-LABEL%3E%3CLINGO-LABEL%3EInterface%20utilisateur%3C%2FLINGO-LABEL%3E%3C%2FLINGO-LABS%3E%3CLINGO-SUB%20id%3D%22lingo-sub-392849%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3EObjet%20%3A%20Am%C3%A9lioration%20des%20tests%20d'%C3%A9quivalence%20dans%20Fit%20Y%20by%20X%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-392849%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CP%3EJe%20suis%20d'accord%20qu'un%20back-solver%20serait%20pratique%20mais%20cela%20va%20%C3%A0%20l'encontre%20de%20l'intention%20d'un%20test%20d'%C3%A9quivalence%20qui%20est%20de%20sp%C3%A9cifier%20un%20seuil%20de%20diff%C3%A9rence%20pratique%3CEM%3E%20avant%3C%2FEM%3E%20ex%C3%A9cutant%20l'exp%C3%A9rience.%26nbsp%3B%26nbsp%3B%3C%2FP%3E%3CP%3EC'est%20un%20peu%20comme%20choisir%20la%20diff%C3%A9rence%20pratique%20entre%20%22passer%22.%3C%2FP%3E%3C%2FLINGO-BODY%3E%3CLINGO-SUB%20id%3D%22lingo-sub-250299%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3EObjet%20%3A%20Am%C3%A9lioration%20des%20tests%20d'%C3%A9quivalence%20dans%20Fit%20Y%20by%20X%3C%2FLINGO-SUB%3E%3CLINGO-BODY%20id%3D%22lingo-body-250299%22%20slang%3D%22en-US%22%20mode%3D%22NONE%22%3E%3CP%3ESi%20vous%20avez%20un%20alpha%3D0%2C05%2C%20un%20intervalle%20de%20confiance%20de%2090%26nbsp%3B%25%20sur%20la%20diff%C3%A9rence%20des%20moyennes%20entre%202%26nbsp%3Bgroupes%20s'alignera%20sur%20la%20valeur%20de%20diff%C3%A9rence%20limite%20que%20vous%20sp%C3%A9cifiez.%20Dans%20la%20plate-forme%20Fit%20Y%20by%20X%2C%20vous%20pouvez%20modifier%20le%20niveau%20alpha%20pour%20dire%200%2C10%20et%20utiliser%20le%20test%20t%20appropri%C3%A9%20pour%20effectuer%20cette%20comparaison%20dans%20l'ensemble%20de%20donn%C3%A9es%20Big%20Class.%3C%2FP%3E%3CP%3E%26nbsp%3B%3C%2FP%3E%3CP%3EEn%20g%C3%A9n%C3%A9ral%20cependant%2C%20ce%20n'est%20pas%20une%20bonne%20pratique%20d'obtenir%20l'intervalle%20de%20confiance%20puis%20de%20d%C3%A9terminer%20si%20ce%20niveau%20de%20diff%C3%A9rence%20est%20significatif%20ou%20non.%20Je%20ne%20peux%20pas%20dire%20%C3%A0%20partir%20de%20votre%20fil%20si%20ce%20d%C3%A9bat%20a%20lieu%20avant%20ou%20apr%C3%A8s%20que%20les%20donn%C3%A9es%20se%20produisent%26nbsp%3B%3B%20naturellement%2C%20nous%20voulons%20que%20cela%20soit%20convenu%20%C3%A0%20l'avance%20afin%20que%20lorsque%20les%20donn%C3%A9es%20reviennent%2C%20le%20groupe%20puisse%20%C3%AAtre%20tenu%20responsable%20du%20seuil%20pr%C3%A9s%C3%A9lectionn%C3%A9.%3C%2FP%3E%3C%2FLINGO-BODY%3E
Choose Language Hide Translation Bar
0 Kudos

Improving Equivalence Tests in Fit Y by X

Suggestion would be to allow an automatic solve for the difference value that gives equivalence for a given alpha.

In the example example-of-an-equivalence-test there would be an option to solve for the difference value that predicts equivalence for a given alpha value (it addition to the current option for supplying a specific difference).   Many times this difference value is specified inconsistently among a given department or functional group (often with many differing opinions).  So, instead of running multiple differences to show the p-values for equivalence it would be very convenient to solve for the difference that would predict equivalence given an alpha value.

2 Comments
jszarka
Level V

If you have an alpha=.05, a 90% confidence interval on the difference in means between 2 groups will align with the boundary difference value you specify. Within the Fit Y by X platform you can change the alpha level to say .10 and use the appropriate t-test for making that comparison in the Big Class data set.

 

In general though, it's not a good practice to get the confidence interval then determine whether or not that difference level is meaningful. I can't tell from your thread whether this debate occurs before or after the data occurs; naturally we want that agreed upon in advance so that when the data comes back the group can be held accountable to the preselected threshold.

I agree that a back-solver would be handy but it goes against the intent of an equivalence test which is to specify a practical difference threshold before running the experiment.  

This is kind of like cherry-picking the practical difference to "pass."