difficulties with my k-means clustering analysis

FrenchOrtho

Hello,

I am having difficulties with my k-means clustering analysis on JASP software.

Indeed, for some of my variables, I have participants who have obtained low scores or even 0. I have the impression that these scores are not taken into account by the algorithm because they do not appear on my t-SNE plot whereas I have the right number of participants in the cluster information table.

The problem is that I can't know the distribution of my participants in each cluster.

How can I proceed?

Thanks in advance,

Manon

koenderks

Hi Manon,

Here I am again. From the top of my head these 0’s are taken into account. However, it is hard to see without looking at what you are looking at. Is it possible for you to save your analyses and upload them as a .jasp file (the default jasp save format) here? Then I can get a better idea of the situation.

Koen

FrenchOrtho

Hello,

I managed to download the results only in PDF and I can't put them in my answer. It doesn't want to work...

Also, I have another difficulty that you might be able to help me with:

The cluster names/numbers change between the cluster information table/cluster mean plots and the t-SNE cluster plot ( for example, cluster number 1 in the information table or cluster mean plots indicates that there are 2 participants in this cluster while the t-SNE indicates that cluster 1 has 9 participants).

 

This is really disturbing for the results of my study because I don't know where to refer to know where my participants are and what are the means of each cluster. I also can't figure out which mean belongs to which cluster.

 

Could you please help me?

 

if not, would it be possible to agree on a telephone or video conference appointment to be guided?

I'm sorry, but I can't go ahead with my final study without these elements, I feel lost

Thank you,

Manon