cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Check out the JMP® Marketplace featured Capability Explorer add-in
Choose Language Hide Translation Bar
mdunlap
Level II

Bootstrapping in JMP 15

In JMP 14, you could right click on the values in the output to obtain bootstrap confidence intervals.   However, in JMP 15, this no longer appears to be an option.   Does anyone know if JMP removed the bootstrap option completely or if they moved it to some other location?   

JMP Bootstrap.PNG

16 REPLIES 16
ih
Super User (Alumni) ih
Super User (Alumni)

Re: Bootstrapping in JMP 15

ih_0-1607377242689.png

 

mdunlap
Level II

Re: Bootstrapping in JMP 15

Here's my "about":

mdunlap_0-1607379018148.png

It looks the same as yours.   I don't see a difference.

ih
Super User (Alumni) ih
Super User (Alumni)

Re: Bootstrapping in JMP 15

Look at the bold line right below the blue banner, mine says "JMP (R) Pro 15.2.1", and yours says "JMP (R) 15.2.1".  I would email JMP Support.

mdunlap
Level II

Re: Bootstrapping in JMP 15

Oh i see that.

 

Strange that my university offers a JMP "Pro" Windows  and Mac version.   I installed the MAC version which does have "Pro" mentioned in the "about" and the bootstrap does work.

 

But, the Windows version does not have "Pro" mentioned.    Maybe I should mention the differences to the IT at the university and see if they can contact JMP about it.

Re: Bootstrapping in JMP 15

Just to clarify so there is no way to do bootstrap forests in JMP?

is there any way i can get a license renewal for JMP pro?

 

thanks,

Sabrina

P_Bartell
Level VIII

Re: Bootstrapping in JMP 15

Your best bet is to contact JMP sales staff to see what your options are.

Victor_G
Super User

Re: Bootstrapping in JMP 15

Hi @BonferrroniGame 


- If you have JMP Pro, you can easily find bootstrap forest under menu "Analyze", and then "Predictive modeling" : Bootstrap Forest.

- If you have JMP, the only way to perform a bootstrap forest is though the use of the "Predictor screening" platform. It won't give you all the details (accuracy metrics of the model, visualizations, profiler...) and flexibility of the "Bootstrap Forest" platform (customization of the number of trees, of split conditions, ...), but you'll have access to the contribution of your factors depending on your response.
It might be a good option to consider if you want to challenge results coming from a decision tree if you don't have access to JMP Pro. 

 

Victor GUILLER
L'Oréal Data & Analytics

"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)