I have 50 datasets each for every year from 1961 to 2010. These datasets keep data about GDP, mortality, natality, etc. My intent is to apply clustering for each dataset and then compare clusters. Each cluster should reflect concept like "Developed country", "Developing country", "Poor Country", etc. Then, I want to discuss about countries, like Brazil, with a high economic growth, and how it moved from cluster "Poor Contry" to " Developing country ".

In brief, I want to apply clustering to show the evolution (or involution) of countries over time, highlighting cluster changing.

I think this method has many drawback. There are better methods to achieve my purpose?


1 Answer 1


You don't want a clustering.

You want a classification, into human concepts.

Try to define these concepts, best in terms of average GDP etc. and in a way that you can explain what the categories are.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.