# Return to Question

3 deleted 4 characters in body

I have a large distance matrix 3400x3400$$3400\times 3400$$.

I need to cluster them hierarchically and then cut the tree into clusters (like a partitional approach).

Which algorithm is most sensitive to finding natural clusters in the data based on the distance matrix?

How can iI evaluate the result? I am planning on using average silhouette coefficient of the tree at various levels to identify the 'natural' clusters from the tree.

thanks, chetThanks

I have a large distance matrix 3400x3400.

I need to cluster them hierarchically and then cut the tree into clusters (like a partitional approach).

Which algorithm is most sensitive to finding natural clusters in the data based on the distance matrix?

How can i evaluate the result? I am planning on using average silhouette coefficient of the tree at various levels to identify the 'natural' clusters from the tree.

thanks, chet

I have a large distance matrix $$3400\times 3400$$.

I need to cluster them hierarchically and then cut the tree into clusters (like a partitional approach).

Which algorithm is most sensitive to finding natural clusters in the data based on the distance matrix?

How can I evaluate the result? I am planning on using average silhouette coefficient of the tree at various levels to identify the 'natural' clusters from the tree.

Thanks

2 edited title

1

# Which hierarchical clustering algorithm ?

I have a large distance matrix 3400x3400.

I need to cluster them hierarchically and then cut the tree into clusters (like a partitional approach).

Which algorithm is most sensitive to finding natural clusters in the data based on the distance matrix?

How can i evaluate the result? I am planning on using average silhouette coefficient of the tree at various levels to identify the 'natural' clusters from the tree.

thanks, chet