cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
  • DownloadSemiconductor Toolkit: Tools to create wafer maps, add wafer geometry to graphics, explore die defects & compare wafers.
  • Discovery Summit 2026: Early User Edition - September 23-24.Register. It's free.
  • Use JMP Clinical with CDISC-compliant data. Review studies, ID safety and efficacy signals & communicate findings with interactive graphics. Register to see how. Aug. 27, 2 pm US ET.

Discussions

Solve problems, and share tips and tricks with other JMP users.
Choose Language Hide Translation Bar
s22d704
Level I

How to display the cutoff value on the ROC curve.

Is there a way to display the cutoff value on the ROC curve with a dot and a number? Please provide a reference example.図1.png

1 ACCEPTED SOLUTION

Accepted Solutions
Victor_G
Super User

Re: How to display the cutoff value on the ROC curve.

Hi @s22d704,

 

You can use the Crosshair tool '"+" symbol) on any graph to display individual X-Y values :

Victor_G_0-1741338492620.png

 

More infos about the tools in JMP :The Tools Menu - JMP User Community

For binary classification models, you can also have a look at Decision Thresholds Report which may help you to assess the impact of the decision threshold value on specificity, sensitivity, precision, accuracy, F1-score, Matthews Correlation Coefficient, ... :

Victor_G_0-1741345163119.png

 

Hope this answer may help you,

Victor GUILLER

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

View solution in original post

1 REPLY 1
Victor_G
Super User

Re: How to display the cutoff value on the ROC curve.

Hi @s22d704,

 

You can use the Crosshair tool '"+" symbol) on any graph to display individual X-Y values :

Victor_G_0-1741338492620.png

 

More infos about the tools in JMP :The Tools Menu - JMP User Community

For binary classification models, you can also have a look at Decision Thresholds Report which may help you to assess the impact of the decision threshold value on specificity, sensitivity, precision, accuracy, F1-score, Matthews Correlation Coefficient, ... :

Victor_G_0-1741345163119.png

 

Hope this answer may help you,

Victor GUILLER

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

Recommended Articles