NAG CL Interface
g03ecc (cluster_hier)
1
Purpose
g03ecc performs hierarchical cluster analysis.
2
Specification
void |
g03ecc (Nag_ClusterMethod method,
Integer n,
double d[],
Integer ilc[],
Integer iuc[],
double cd[],
Integer iord[],
double dord[],
NagError *fail) |
|
The function may be called by the names: g03ecc, nag_mv_cluster_hier or nag_mv_hierar_cluster_analysis.
3
Description
Given a distance or dissimilarity matrix for
objects (see
g03eac), cluster analysis aims to group the
objects into a number of more or less homogeneous groups or clusters. With agglomerative clustering methods, a hierarchical tree is produced by starting with
clusters, each with a single object and then at each of
stages, merging two clusters to form a larger cluster, until all objects are in a single cluster. This process may be represented by a dendrogram (see
g03ehc).
At each stage, the clusters that are nearest are merged, methods differ as to how the distance between the new cluster and other clusters are computed. For three clusters
,
and
let
,
and
be the number of objects in each cluster and let
,
and
be the distances between the clusters. Let clusters
and
be merged to give cluster
, then the distance from cluster
to cluster
,
can be computed in the following ways:
-
1.Single link or nearest neighbour: .
-
2.Complete link or furthest neighbour: .
-
3.Group average: .
-
4.Centroid: .
-
5.Median: .
-
6.Minimum variance: .
If the clusters are numbered then, for convenience, if clusters and , , merge then the new cluster will be referred to as cluster . Information on the clustering history is given by the values of , and for each of the clustering steps. In order to produce a dendrogram, the ordering of the objects such that the clusters that merge are adjacent is required. This ordering is computed so that the first element is . The associated distances with this ordering are also computed.
4
References
Everitt B S (1974) Cluster Analysis Heinemann
Krzanowski W J (1990) Principles of Multivariate Analysis Oxford University Press
5
Arguments
-
1:
– Nag_ClusterMethod
Input
-
On entry: indicates which clustering.
- Single link.
- Complete link.
- Group average.
- Centroid.
- Median.
- Minimum variance.
Constraint:
, , , , or .
-
2:
– Integer
Input
-
On entry: the number of objects, .
Constraint:
.
-
3:
– double
Input/Output
-
On entry: the strictly lower triangle of the distance matrix. must be stored packed by rows, i.e., , must contain .
On exit: is overwritten.
Constraint:
, for .
-
4:
– Integer
Output
-
On exit:
contains the number,
, of the cluster merged with cluster
(see
iuc),
, at step
, for
.
-
5:
– Integer
Output
-
On exit: contains the number, , of the cluster merged with cluster , , at step , for .
-
6:
– double
Output
-
On exit: contains the distance , between clusters and , , merged at step , for .
-
7:
– Integer
Output
-
On exit: the objects in dendrogram order.
-
8:
– double
Output
-
On exit: the clustering distances corresponding to the order in
iord.
contains the distance at which cluster
and
merge, for
.
contains the maximum distance.
-
9:
– NagError *
Input/Output
-
The NAG error argument (see
Section 7 in the Introduction to the NAG Library CL Interface).
6
Error Indicators and Warnings
- NE_ALLOC_FAIL
-
Dynamic memory allocation failed.
- NE_BAD_PARAM
-
On entry, argument
method had an illegal value.
- NE_DENDROGRAM
-
A true dendrogram cannot be formed because the distances at which clusters
have merged are not increasing for all steps, i.e., for
some . This can occur for the and methods.
- NE_INT_ARG_LT
-
On entry, .
Constraint: .
- NE_INTERNAL_ERROR
-
An internal error has occurred in this function. Check the function call and any array sizes. If the call is correct then please contact
NAG for assistance.
- NE_REALARR
-
On entry, .
Constraint: , for .
7
Accuracy
For methods other than or , slight rounding errors may occur in the calculations of the updated distances. These would not normally significantly affect the results, however there may be an effect if distances are (almost) equal.
If at a stage, two distances and , or and , are equal then clusters and will be merged rather than clusters and . For single link clustering this choice will only affect the order of the objects in the dendrogram. However, for other methods the choice of rather than may affect the shape of the dendrogram. If either of the distances or are affected by rounding errors then their equality, and hence the dendrogram, may be affected.
8
Parallelism and Performance
g03ecc is not threaded in any implementation.
The dendrogram may be formed using
g03ehc. Groupings based on the clusters formed at a given distance can be computed using
g03ejc.
10
Example
Data consisting of three variables on five objects are read in. Euclidean squared distances based on two variables are computed using
g03eac, the objects are clustered using
g03ecc and the dendrogram computed using
g03ehc. The dendrogram is then printed.
10.1
Program Text
10.2
Program Data
10.3
Program Results