JMP User Community

Latest Discussions

reporting R-square for customised nonlinear model fit

I am trying to find the best way to report a nonlinear model fit to my experimental data. I have managed to write a script that fits a nonlinear model and finds the parameters estimates using the loss function. It then reports each parameter estimates and the non linear errors. However, I would like to get the RMSE or R-square of the resulting fit also. Is this not available for nonlinear model...
ivomdb

Discussions |
Sep 26, 2018 9:44 AM

6765 views | 3 replies
Column formula to round timestamp to nearest minute

Hi,Looking for a column formula to round timestamp to nearest minute. 27/06/2017 12:21:13 PM need to round to 27/06/2017 12:21:00 PM.Any suggestions?Cheers.
Onjai

Discussions |
Sep 26, 2018 9:31 AM

14721 views | 5 replies
Cross Correlation Prediction

Hi,I have data and cross correlation in between group (L1& L3), (L1 & L4), (L2 &L3),and (L2 &L4).Can one predict what the correlation between group (L1 & L2) or (L3& L4) is from above correlations? Thanks for your help.
AT

Discussions |
Sep 26, 2018 7:19 AM

4787 views | 2 replies
Dynamic Time Warping DTW

I'm a bit confused about how to use DTW. My data ~300K rows with:1st column - test number 1 to 42nd column - time. For each test, time starts at 0 and goes up in increments of 0.2 ms.Eight columns of measurements.Rows are ordered by test and time. What is the proper way to align with DTW? Thanks
RonB

Discussions |
Sep 26, 2018 4:10 AM

4811 views | 3 replies
Filter Distribution Output by Count (N) of Data Points

I want to use the Distribution function to explore data. The data is tagged by Region. The Regions are of varying sizes.
There are too many Regions to analyze visually.
I'd like to be able to set a filter, say N=25, and only see the graphs for the where the Region has at least 25 data points.

Is that possible?

In the image "Store Cluster" is equivalent Region.

BSwid

Discussions |
Sep 25, 2018 4:18 PM

7039 views | 2 replies

Previous
Next

Latest Discussions

reporting R-square for customised nonlinear model fit

I am trying to find the best way to report a nonlinear model fit to my experimental data. I have managed to write a script that fits a nonlinear model and finds the parameters estimates using the loss function. It then reports each parameter estimates and the non linear errors. However, I would like to get the RMSE or R-square of the resulting fit also. Is this not available for nonlinear model...
ivomdb

Discussions |
Sep 26, 2018 9:44 AM

6765 views | 3 replies
Cross Correlation Prediction

Hi,I have data and cross correlation in between group (L1& L3), (L1 & L4), (L2 &L3),and (L2 &L4).Can one predict what the correlation between group (L1 & L2) or (L3& L4) is from above correlations? Thanks for your help.
AT

Discussions |
Sep 26, 2018 7:19 AM

4787 views | 2 replies
Dynamic Time Warping DTW

I'm a bit confused about how to use DTW. My data ~300K rows with:1st column - test number 1 to 42nd column - time. For each test, time starts at 0 and goes up in increments of 0.2 ms.Eight columns of measurements.Rows are ordered by test and time. What is the proper way to align with DTW? Thanks
RonB

Discussions |
Sep 26, 2018 4:10 AM

4811 views | 3 replies
probit analysis - fit testing (regression) and replicates

I'm trying to determine the ec50 (concentration at which there is 50% radial fungal growth compared to the control) of certain fungicides I've tried in vitro (in petri dishes) vs different isolates. I have tested the same 9 different isolates with different fungicides as radial mycelium growth. For every fungicide there are 5, 6 or 7 (depending on the fungicide) concentrations tested and 3 replica...
stavpal

Discussions |
Sep 25, 2018 12:08 PM

8452 views | 4 replies
how to change the type and color of lines in graph

I am trying to show line of fit in graph builder for several sets of data. The data table have many columns, I want to show the column(i) vs column(1).Every column can be grouped by A1 & a, also can be grouped by B1 & b, but except column(1). The follow is the chart about column(2) vs column(1): I use the follow script to change the type of lines:Dispatch( {}, "400", ScaleBox, {Legend Model( 8,...
Yu

Discussions |
Sep 25, 2018 2:34 AM

3632 views | 0 replies

Previous
Next

Latest Discussions

how to change the type and color of lines in graph

I am trying to show line of fit in graph builder for several sets of data. The data table have many columns, I want to show the column(i) vs column(1).Every column can be grouped by A1 & a, also can be grouped by B1 & b, but except column(1). The follow is the chart about column(2) vs column(1): I use the follow script to change the type of lines:Dispatch( {}, "400", ScaleBox, {Legend Model( 8,...
Yu

Discussions |
Sep 25, 2018 2:34 AM

3632 views | 0 replies
Mean separation letter from test slices

Hello!

How do I get the mean separation letter in for each level of a factor when interaction is significant? For example, if I have A*B interaction and I want to get the mean separation of B at each level of A, how do I get the LSD letters in JMP? I can do test slices and that will use the DF of the full analysis, but this does not shows which mean of B differs. If I do multiple comparison: How ca...
jfranc19

Discussions |
Sep 14, 2018 2:35 PM

2455 views | 0 replies
repeated-measures ANCOVA: How to perform the analysis when the parallel slope assumpt. doesn't meet?

Hi all,I need to perform the ANCOVA for a repeated-measures design. I tried to adapt the Julian's ANCOVA procedure showed on the https://www.youtube.com/watch?v=mApbp1RDy-U to my study case (repeated-measures design). Initially, I did the following actions: 1. In the Fit Y by X dialogue: I selected VAR_Y as "Y, Response" and VAR_X as "X, Factor";2. For "Group by" I selected the variable Timepoint;...
Reinaldo

Discussions |
Jun 18, 2018 6:31 AM

3433 views | 0 replies
Time Series - Prewhiten

Hello Everyone, My question pertains to understanding what the terminology in JMP's prewhiten platform means.Also, understanding how that helps me determine an appropriate Transfer Function that I can use to test whether x causes y. JMP's prewhiten output shows three different ACF's labeled "Prewhiten Corr", "Noise AutoCorr", & "Noise Partial AutoCorr".
What is the Prewhiten Corr, Noise AutoCorr, &...
nopon649

Discussions |
Jun 7, 2018 11:10 PM

2467 views | 0 replies
Fit Spline By Group: Save Spline Coefficients to Column?

Hi all--having an issue. I am using Fit Y by X to fit 5,000 separate regressions. I hold control, select red drop-down arrow, and Fit->Flexible, Fit->Spline and select, say, 0.1. This fits a spline to all 5,000 graphs with lambda of 0.1. I have 28 X values in each of 5,000 graphs, and I understand there are 4 different spline coefficients (A, B, C, D). I understand if I just had 1 regression...
M0gAl0g

Discussions |
Jun 5, 2018 3:19 PM

3023 views | 0 replies