Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

Highlighted

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Oct 17, 2020 10:49 AM
(154 views)

Hi, I'm fairly new to JMP and have been using it for a small research project. (I'm just learning, and am a student not a statistician, but really like how intuitive the analyses are to run and the number and types of analyses supported.)

__ I'm struggling with putting together a Fisher's Exact Test for a small number of nominal data__. I have 10 subjects who had their limb pulse measured before and after tourniquet application, then after two movements with the tourniquet on.

(online calculators like the one at socscistatistics.com do give me the data I'm looking for, but I can't seem to do it in JMP)

My data table looks like this:

Before Tourniquet | After Apply Tourniquet | After Move 1 | After Move 2 |

Yes | No | Yes | No |

Yes | No | No | Yes |

Yes | No | No | No |

Yes | No | No | No |

Yes | No | No | Yes |

Yes | No | No | Yes |

Yes | No | No | Yes |

Yes | No | Yes | No |

Yes | No | Yes | No |

Yes | No | No | Yes |

I've also tried setting it up like this:

After Apply | After Move 1 | |

Pulse Yes | 0 | 3 |

Pulse No | 10 | 7 |

But, again, getting the same thing in Y by X, which looks like the screenshot below.

How can / should I be setting this up so that I can get statistical data of pulse after move 1 vs pulse after apply?

Thanks for any assistance,

Ari

```
Contingency(
Y( :After Apply ),
X( :After Move 1 ),
Contingency Table,
Fisher's Exact Test( 1 )
)
```

1 ACCEPTED SOLUTION

Accepted Solutions

Highlighted
I'm not sure what question you are trying to answer? Is the question: What is the affect of moves on pulse? Or does pulse change with moves? I attached the JMP data table as I think it might be setup. I also added a script you can click on to see the analysis.

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

3 REPLIES 3

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Please Help with Fisher's Exact Test?

Created:
Oct 17, 2020 11:15 AM
| Last Modified: Oct 17, 2020 11:30 AM
(148 views)
| Posted in reply to message from adoucette 10-17-2020

Your data has 2 dimensions, When the Tourniquet was applied, and Applied before or after a move. Therefore, the data needs to be setup like the image below

Tourniquet | After Move |

Before | Yes |

After | Yes |

Before |
No |

Before | Yes |

After | No |

Before | No |

After | Yes |

The Fit Y by X platform can then be opened and the Tourniquet column used as the Y Response column, and the After Move used as the X Factor column

Jim

Highlighted
I'm not sure what question you are trying to answer? Is the question: What is the affect of moves on pulse? Or does pulse change with moves? I attached the JMP data table as I think it might be setup. I also added a script you can click on to see the analysis.

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Highlighted
##

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: Please Help with Fisher's Exact Test?

Thank you @txnelson and @statman. Both of the suggested solutions worked. You were correct that I needed to set the data table up a bit differently.

Statman, I'm testing if the pulse changes with moves. (So, for a tourniquet that initially made the pulse on that limb go away, return of pulse after the moves suggests that the moves may have caused the tourniquet to fail to make the pulse go away.)

Thanks again,

Ari