Importing Data

Question

Hello,

I'm using JMP 8 and I have a question: is it possible to import an already existing similarity matrix so that I can I apply clustering to it? As far as I understand, JMP handles the data in the table as individual datapoints and then applys a distance function of them to calculate for example the distance between data point A and B. But I have already the distances between these points and it is not possible to express them as individual values of A and B. So, can I import such an matrx and then apply just the clustering algorithms on it?

hengdai · Answer

Hi Jeff,

I have a similar situation and I have JMP9.

Basically I have a distance matrix of N*N and I opened it in JMP. Then I tried to use the Analyze->Multivariant -> Cluster. Then I clicked the Data is Distance Matrix and clicked OK button. Then nothing happened. Exactly how do I do it?

Thanks,

Heng

unknown · Answer

Thanks for your answer. Perhaps, can you point me to an example or other ongoing documentation? I'm not sure how the similarity matrix should look like when I open it for clustering?

Jeff_Perkinson · Answer

Hi Thomas,

There's no option in JMP 8 to use a matrix exactly as you describe. However, our experience is that using a similarity or distance matrix as input to the clustering platform as if it was raw data will generally give similar results results to what you would have gotten with the raw data. We do that frequently in our JMP Genomics product.

JMP 9 will take a distance matrix directly in the Clustering platform.

I hope that helps.

Jeff