Determining ideal number of clusters for sequence(distance)- based clustering

Question

I have written these functions for clustering sequence-based data:

library(TraMineR)
library(cluster)

clustering <- function(data){
  data <- seqdef(data, left = "DEL", gaps = "DEL", right = "DEL")
  couts <- seqsubm(data, method = "CONSTANT")
  data.om <- seqdist(data, method = "OM", indel = 3, sm = couts)
  clusterward <- agnes(data.om, diss = TRUE, method = "ward")
  (clusterward)
}

rc <- clustering(rubinius_sequences)

cluster_cut <- function(data, clusterward, n_clusters, name_clusters){
  data <- seqdef(data, left = "DEL", gaps = "DEL", right = "DEL")
  cluster4 <- cutree(clusterward, k = n_clusters)
  cluster4 <- factor(cluster4, labels = c("Type 1", "Type 2", "Type 3", "Type 4"))
  (data[cluster4==name_clusters,])
}

rc1 <- cluster_cut(project_sequences, rc, 4, "Type 1")

However, here the number of clusters is arbitrarily assigned. Is there some way I can show that the amount of variance (or some similar measure) captured by a certain number of clusters starts to reach a point of diminishing returns at a certain number of clusters? I'm imagining something similar to a scree plot in factor analysis.

Answer 1

library(WeightedCluster)  
(agnesRange <- wcKMedRange(rubinius.dist, 2:10))
plot(agnesRange, stat = c("ASW", "HG", "PBC"), lwd = 5)

This will give multiple indices for finding the ideal number of clusters, as well as as graph. More information about the indices can be found here (under cluster quality): http://mephisto.unige.ch/weightedcluster/