Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar
Highlighted
Jasen
Level I

JMP Data analysis

Hi JMP community,

 

I Am more of a qualitative type, and quantitative measures have never really been my strong suit.

 

I was wondering if anyone here could point me in the right direction and help me with my data analysis, using JMP :)

 

Kind regards, a weary student 

1 ACCEPTED SOLUTION

Accepted Solutions
Highlighted

Re: JMP Data analysis

Your brief posting leave me a bit unclear but lets proceed anyway. You did not specify your experience using JMP so if you are a new user, I suggest you select Help > Books and look at two guides: Discovering JMP and Using JMP. They will help you a lot, even if you just skim through them.

 

You measurements should be stored in a data column with the Numeric data type and the Continuous modeling type. Any labels or categories may be stored in data columns using either the Numeric or the Character data type and either the Nominal or Ordinal modeling type.

 

I suggest that you follow this path to safely and confidently explore your data and potential relationships:

 

  • Examine the variables separately. Select Analyze > Distribution and enter all the measurements in the Y role.
    • Is the range of values realistic?
    • Are any values unexpected?
    • Is the distribution of values reasonable?
  • Examine the variables together in pairs. Select Analyze > Multivariate Methods > Multivariate and enter all the measurements in the Y role.
    • Are the linear correlations in the table interpretable?
    • Are the linear correlations expected?
    • Use the scatter plots to understand the linear correlations.
    • Are there any unusual observations?
  • Examine the relationships. Select Analyze > Fit Model. Select the columns with the outcomes and click Y. Select the potential factors or predictors and click Add. Then click Run.
    • The Fit Least Squares platform presents a lot of information of different types and at different levels of the regression analysis. I will wait to hear what you found and with what you might need help.

 

Is this helpful?

Learn it once, use it forever!

View solution in original post

5 REPLIES 5
Highlighted

Re: JMP Data analysis

I am sure that you will find help here. Also, the JMP documentation is broad and deep. But we have no idea how or where to direct you. Please describe the nature of the data and the questions you hope to answer.

Learn it once, use it forever!
Highlighted
Jasen
Level I

Re: JMP Data analysis

Hi Mark,
 
Thank you so much for getting back to me, i apologize for my late reply, I have been attempting to clean the data so that i am able to work with it.
 
I am dealing with Eye-tracking and Galvanic Skin Response data
 
I'm looking to explain how cognitive and emotional responses may influence altruist vs non-altruist prosocial decision-making in gain vs loss choice tasks. Using two neurotechniques tools: Eye-Tracking (AOI) and Galvanic Skin Response.
 
I have managed to stack and join the data in JMP, and looking to answer whether there are any correlations in my data, but am finding it tricky to approach :(
 
 
Highlighted

Re: JMP Data analysis

Your brief posting leave me a bit unclear but lets proceed anyway. You did not specify your experience using JMP so if you are a new user, I suggest you select Help > Books and look at two guides: Discovering JMP and Using JMP. They will help you a lot, even if you just skim through them.

 

You measurements should be stored in a data column with the Numeric data type and the Continuous modeling type. Any labels or categories may be stored in data columns using either the Numeric or the Character data type and either the Nominal or Ordinal modeling type.

 

I suggest that you follow this path to safely and confidently explore your data and potential relationships:

 

  • Examine the variables separately. Select Analyze > Distribution and enter all the measurements in the Y role.
    • Is the range of values realistic?
    • Are any values unexpected?
    • Is the distribution of values reasonable?
  • Examine the variables together in pairs. Select Analyze > Multivariate Methods > Multivariate and enter all the measurements in the Y role.
    • Are the linear correlations in the table interpretable?
    • Are the linear correlations expected?
    • Use the scatter plots to understand the linear correlations.
    • Are there any unusual observations?
  • Examine the relationships. Select Analyze > Fit Model. Select the columns with the outcomes and click Y. Select the potential factors or predictors and click Add. Then click Run.
    • The Fit Least Squares platform presents a lot of information of different types and at different levels of the regression analysis. I will wait to hear what you found and with what you might need help.

 

Is this helpful?

Learn it once, use it forever!

View solution in original post

Highlighted
Jasen
Level I

Re: JMP Data analysis

It is my first time using JMP, and the information you have just given me is very very helpful. 

 

The part suggesting how to 'explore your data and potential relationships' Is just what i was looking for.

 

Thank you so much, really greatful for you taking your time to point me in the right direction.

 

Hopefully i can reach out again should i hit some stumbling blocks along the way.

Highlighted
peace
Level I

Re: JMP Data analysis

hey Mark, as a student we were tasked to design simple experiments using JMP and analyse our results after actually carrying out the experiments. The aim of my experiment was to determine the effect of different factors on the evaporation rate of water in a microwave. My factors were 1.) vol of h20 2.) power setting of MW 3). bowl size 4.) time.
All my factors have turned out to be statistically insignificant. so on asking JMP to run the model, an alert pops up; 'the model lacks an effect'.
please advise me, what am I doing wrong? did i choose the wrong design(classical>screening design>full factorial). am a novice
Article Labels

    There are no labels assigned to this post.