MEBA not working - data unbalanced


I am working on statistical analysis [metadata table] module. In particular, I use time-series + one factor design. My data are expressed as concentrations.
I have 3 different treatments (Phenotypes), 4 time-points (Time), and 4 Subjects per phenotype-time point. Therefore 48 samples in total. These are the .csv files I use:
Data_MA_meba issue.csv (9.0 KB)
Meta_MA_meba issue.csv (871 Bytes)

I do not normalize the samples or transform the data, but I apply auto scaling.
The data check detected 0 missing values, and all the statistical analyses are working (ANOVA2, ASCA, Heatmap, etc).
When I try the MEBA, I get this error:

  • Error Please make sure data are balanced for time-series analysis. In particular, for each time point, all experiments must exist and cannot be missing!

The point is that the data are balanced and no experiment is missing, I checked the matrix over and over again.

Has anyone experienced the same problem? Any suggestions as to what the error might be?

Thanks in advance for your help.

Please follow our post guidelines

Hello Jeff, I updated the topic following the guidelines

The issue is fixed and you can try again after server update during the weekend. It is related to weak signals in your data (i.e. nothing pass the default threshold).

This topic was automatically closed after 3 days. New replies are no longer allowed.