JMP User Community

Latest Discussions

labeling points on PCA Score plot

I ran a PCA on my data and want to modify the score plot so that I can label each point according to a column value. This seems like a pretty obvious thing to want to do but I can't seem to figure out how to do it. Also, is there a straightforward way to access the plots directly rather than in the tiny window with all the PCA results? I'd appreciate any pointers for this obvious newbie, even j...
treebat

Discussions |
Aug 6, 2010 8:23 AM

4347 views | 2 replies
Help for an experimentalist

Is there a straightforward way to run a simple analysis of covariance, and receive the ANOVA table as output?

How about any estimate of effect size, such as Cohen's d, Eta-squared, or Omega-squared?

Any way to receive actual group means instead of least squares means in the post-hoc analyses? (see: http://onbiostatistics.blogspot.com/2009/04/least-squares-means-marginal-means-vs.html)

Discussions |
Jul 30, 2010 10:53 AM

2436 views | 0 replies
Binning Continues Date Time data

Is there any way in JMP to convert a column of date time (continuous) into categorical data bins (also date time). For example 6 hour bins..?

Discussions |
Jul 30, 2010 10:34 AM

3862 views | 1 replies
Using PRESS criteria to build multilinear models

Hello,
When using the Stepwise platform, JMP helps you to make the model with the best R² / R²adj.
I would like to get the model with the best PRESS criteria (Predicted Error Sum of Squares). How would it be possible to do that?
I know you can get the PRESS information once the model is built, but I would like to be sure I am building the model with the best PRESS as possible.
Thank you for your help...
dp30

Discussions |
Jul 21, 2010 11:44 PM

4535 views | 2 replies
Save Inverse Prediction Formula

For some reason the command "Save Inverse Prediction Formula", does not save the formula to the associated table. The command "Custom Inverse Prediction" works and does calculate one of the two possible X variable solutions (the function is a Gaussian curve and therefor has two X solutions for each Y variable). But I can not seem to get the formula to save as a new column.

I have read the docs on ...
kray

Discussions |
Jul 19, 2010 6:58 AM

3861 views | 1 replies

Previous
Next

Latest Discussions

labeling points on PCA Score plot

I ran a PCA on my data and want to modify the score plot so that I can label each point according to a column value. This seems like a pretty obvious thing to want to do but I can't seem to figure out how to do it. Also, is there a straightforward way to access the plots directly rather than in the tiny window with all the PCA results? I'd appreciate any pointers for this obvious newbie, even j...
treebat

Discussions |
Aug 6, 2010 8:23 AM

4347 views | 2 replies
Help for an experimentalist

Is there a straightforward way to run a simple analysis of covariance, and receive the ANOVA table as output?

How about any estimate of effect size, such as Cohen's d, Eta-squared, or Omega-squared?

Any way to receive actual group means instead of least squares means in the post-hoc analyses? (see: http://onbiostatistics.blogspot.com/2009/04/least-squares-means-marginal-means-vs.html)

Discussions |
Jul 30, 2010 10:53 AM

2436 views | 0 replies
Binning Continues Date Time data

Is there any way in JMP to convert a column of date time (continuous) into categorical data bins (also date time). For example 6 hour bins..?

Discussions |
Jul 30, 2010 10:34 AM

3862 views | 1 replies
Using PRESS criteria to build multilinear models

Hello,
When using the Stepwise platform, JMP helps you to make the model with the best R² / R²adj.
I would like to get the model with the best PRESS criteria (Predicted Error Sum of Squares). How would it be possible to do that?
I know you can get the PRESS information once the model is built, but I would like to be sure I am building the model with the best PRESS as possible.
Thank you for your help...
dp30

Discussions |
Jul 21, 2010 11:44 PM

4535 views | 2 replies
Save Inverse Prediction Formula

For some reason the command "Save Inverse Prediction Formula", does not save the formula to the associated table. The command "Custom Inverse Prediction" works and does calculate one of the two possible X variable solutions (the function is a Gaussian curve and therefor has two X solutions for each Y variable). But I can not seem to get the formula to save as a new column.

I have read the docs on ...
kray

Discussions |
Jul 19, 2010 6:58 AM

3861 views | 1 replies

Previous
Next

Latest Discussions

Help for an experimentalist

Is there a straightforward way to run a simple analysis of covariance, and receive the ANOVA table as output?

How about any estimate of effect size, such as Cohen's d, Eta-squared, or Omega-squared?

Any way to receive actual group means instead of least squares means in the post-hoc analyses? (see: http://onbiostatistics.blogspot.com/2009/04/least-squares-means-marginal-means-vs.html)

Discussions |
Jul 30, 2010 10:53 AM

2436 views | 0 replies
Control Charting with transactional recordset

Hello,

I'm trying to understand if JMP supports a control chart graph directly from transactional data without first having to create a summary table.

The JMP sample data table called Washers contains 15 records showing the count of defects per lot size of 400. Taking one step back there may have existed a data table of 6000 records (15x400) where each record contained the defect count of 1 or 0. W...
khill

Discussions |
May 10, 2010 4:40 AM

2360 views | 0 replies
Nemenyi test post-hoc for Kruskal-Wallis test

Is there a way to do post-hoc testing for the Kruskal-Wallis test for non-parametric data? I have searched the web and most use the Nemenyi test as described by Zar in Biostatistical analysis 3rd edition p226. I have a large amount of data and don't want to do all this by hand.

Many thanks

Discussions |
Feb 12, 2010 12:10 AM

3201 views | 0 replies
Random Parameters in Profiler?

I am evaluating JMP (currently V. 7, but my company is in the upgrade process) and I am particularly interested in figuring out how to use the Profiler for some of my frequent activities. Can anyone help with the following?

I would like to simulate a function F(x, theta(i)) over a range of x values. Theta(i) is a set of parameters drawn from a multivariate-normal distribution for each individual ...
jff

Discussions |
Jun 25, 2009 5:53 AM

2787 views | 0 replies
Overlay normal quantile plots without long string labels

Hello,

I am a longtime user of JMP7. To make overlay normal quantile plots I use Fit Y by X, where Y is the continual variable like Height and X is a categorical variable like Gender. Using Right-click/Legend gives a nice color coded legend for the curves, but JMP also tries to label each curve way up at the top (upper quantile) end of the curve. Invariably these are ugly and overlap each other. ...
karenb

Discussions |
Jun 2, 2009 5:54 PM

3347 views | 0 replies