JMP User Community

Latest Discussions

Logistic Regression Results Question: Large OR, Small Chisq, No CIs

Hello, Having some trouble interpreting data from a logistic regression. Attempting to determine if various drugs were associated with outcome in a case-control study. Using logistic regression because I want to control for two co-variates (age and site of disease onset). For one drug, the nominal logistic spits out a huge OR, small Chisq, and no CIs (see photo). When I run the model with each co-...
dsharri3

Discussions |
Mar 31, 2017 1:00 PM

5903 views | 5 replies
add rows based on a column values in the same data table

Dear All,I have data table that contain ID, last inspection data, and last inspection decision columns. I want to combine the last inspection data column with the last inspection decision in order to have one column (stacked) to be used in association analysis. For instance, one cluster of my data structure looks like the following:ID Last Inspection Decision Last Inspection...
qais_hatim_fda_

Discussions |
Mar 31, 2017 9:09 AM

8711 views | 3 replies
Unrounded degrees of freedom

I am doing an independent sample t-test, and I've encountered a problem with the degrees of freedom. What I'd like to do is use the floor (13 in the attached analysis), not the unrounded (13.65148), df, in calculating the confidence interval and p value. Is there a setting I can change in JMP so that it uses the floor of the df? Thank you.
forgottendino

Discussions |
Mar 30, 2017 10:14 AM

9826 views | 4 replies
Column difference- JSL syntax

Hi All, How to access the contents of a column by the column reference? Since my column names keep changing with every loop in the script, I can't just simple use the column name to subtract. dt is my data table and has 30 columns. I want to create a new column with dt[28]- dt[30]. Can anyone help me with syntax? I really appreciate it. Thank you.
vishwasanj

Discussions |
Mar 30, 2017 2:36 AM

10542 views | 5 replies
Blocking in factorial Design

I would like to set up a full factorial 2^4 design with a three level block (48 experiments).In JMP Pro 13, is there an way to include a blocking variable through DOE>Classical>Screening Design? I see an option under DOE>Custom Design to add a blocking variable. Thanks.
paul1

Discussions |
Mar 29, 2017 12:05 PM

13936 views | 4 replies

Previous
Next

Latest Discussions

Logistic Regression Results Question: Large OR, Small Chisq, No CIs

Hello, Having some trouble interpreting data from a logistic regression. Attempting to determine if various drugs were associated with outcome in a case-control study. Using logistic regression because I want to control for two co-variates (age and site of disease onset). For one drug, the nominal logistic spits out a huge OR, small Chisq, and no CIs (see photo). When I run the model with each co-...
dsharri3

Discussions |
Mar 31, 2017 1:00 PM

5903 views | 5 replies
How to globally set levels in a chart

I have a few scripts that I use that were created from charts. Often these charts have data that JMP separates into levels although for my purposes, they are effectively the same. For example the following code is for a chart of mean exclusion rates across sites.Chart( X(:IDENT Code), Y(Mean(:Exclusion Rate)), Add Error Bars to Mean(Name("Confidence Interval (pooled)")(0.95)), Overlay ...
mdawson69

Discussions |
Mar 21, 2017 8:03 AM

6960 views | 5 replies
CCC Optimal

Hi,I have 2 clustering chooses as mentionned below,- Nr of cluster 15 : CCC = 69.99 (OPTIMAL)- Nr of cluster 15 : CCC = -92.87- Nr of cluster 15 : CCC = -112.8 The first one with CCC = 69.99 is mentionned as the best optimal. I don't understand why this one is the best by consedering the different values ?. What is the signification of these values ? Thanks,
Lamine

Discussions |
Mar 17, 2017 5:25 AM

3346 views | 0 replies
Get count for grouping (panels) in graph builder to check the visualisation is sensible

So I have written a bit of JSL which is able to take a data table and make suggestions of graphs. It checks the number of unique values, column data type and column name to assess which graph would be most appropriate. One issue I am having is when it uses Page, Group X, Group Y and/or Wrap and there aren't many data points in the resulting panels. Below is a silly example using Big Class. Clearly...
stephen_pearson

Discussions |
Mar 16, 2017 6:00 AM

5780 views | 4 replies
Non-Modal windows/user-interactive script

Hi, Details of my script:Part 1: open a new table so that user fills valuesPart 2: wait for the user to fill values and take the response to proceedPart 3: proceed with the remaining script I am struggling in part 2 because if I use Modal windows, I cannot fill the values in the table.I would like to generate a new window which will wait on user input OK" to proceed but should not interrupt the us...
shashivenky

Discussions |
Mar 9, 2017 4:16 AM

5080 views | 2 replies

Previous
Next

Latest Discussions

CCC Optimal

Hi,I have 2 clustering chooses as mentionned below,- Nr of cluster 15 : CCC = 69.99 (OPTIMAL)- Nr of cluster 15 : CCC = -92.87- Nr of cluster 15 : CCC = -112.8 The first one with CCC = 69.99 is mentionned as the best optimal. I don't understand why this one is the best by consedering the different values ?. What is the signification of these values ? Thanks,
Lamine

Discussions |
Mar 17, 2017 5:25 AM

3346 views | 0 replies
Understanding the Dispatch and Legend Model and what exactly is Base(0,0,0)?

My problem is two fold. Im writing a JSL Function to create some custom charts at work. Everything is working fine. Thats great. But I dont understand why - and I am trying to break down the code. Most of I wrote myself, but some aspects I made the tweaks within JMP, copied the scripts and used the parts that generated what I needed. Some of the code chunks that get added in are intuitive to read ...
kevinwtbolger

Discussions |
Feb 26, 2017 9:30 AM

3386 views | 0 replies
Data Binding Associative Arrays

I recently had need to create some slightly complex data structures and started to play with associative arrays a little more. These are similar to dictionaries in other languages. Where they differ is that most languages to improve speed, when assigning an object in a dictionary to a variable it does a data binding. Essentially it makes it so both the dictionary and the variable refer to the s...
msharp

Discussions |
Feb 14, 2017 1:53 PM

4422 views | 0 replies
How to Maintain JMP Graphs Table Layout When Copy and Pasting into Word

For years I've had to build sets of graphs using the Fit Y by X platform. The graphs are simple: X-axis is always (1) a character, nominal column and (2) a numeric, continuous date/time column. The Y-axis is always numeric, continuous data (bins, registers, parameters). The result is a list of box plot on the left, time trend on the right. There could be many plots at a time. In JMP 12 (and I thin...
MIKE

Discussions |
Dec 14, 2016 8:48 AM

4753 views | 0 replies
Odds ratios for multiway tables

On twitter earlier today, someone asked if the Cochran-Mantel-Haenszel (CMH) odds ratio (OR) test was available in JMP when the stratification variable is not the X in Fit Y by X. Anytime I need to go from two variables to more than two variables, the first place I look is Fit Model. The beauty of fit model is that not only can I use as many variables as I want, but I can consider interactions bet...
DonMcCormack

Discussions |
Aug 10, 2016 3:35 PM

4905 views | 0 replies