Im reading the answer on "how to determine number of clusters in EM algorithm". How to tell if data is "clustered" enough for clustering algorithms to produce meaningful results?

One of the answers is:

When you don't have any idea of what you would expect to find if there was noise only, a good approach is to use resampling and study clusters stability. In other words, resample your data (via bootstrap or by adding small noise to it) and compute the "closeness" of the resulting partitions, as measured by Jaccard similarities. In short, it allows to estimate the frequency with which similar clusters were recovered in the data.

How is this done exactly? Say I perform k cluster EM on N bootstrapped samples and it I receive kxN means and kxN covariance matrices. How then do I go from there to measuring the stability of EM? The jacaard similarity seems to be a measurement on sets rather than on Mixture gaussian distributions?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.