Partitioning Around Medoids (PAM)
Return a partitioning (clustering) of the data into
pam(x, k, diss = inherits(x, "dist"), metric = "euclidean", stand = FALSE)
- data matrix or data frame, or dissimilarity matrix or object,
depending on the value of the
In case of a matrix or data frame, each row corresponds to an observation, and each column corresponds to a variable. All
- positive integer specifying the number of clusters, less than the number of observations.
- logical flag: if TRUE (default for
xwill be considered as a dissimilarity matrix. If FALSE, then
xwill be considered as a matrix of observations by var
- character string specifying the metric to be used for calculating dissimilarities between observations. The currently available options are "euclidean" and "manhattan". Euclidean distances are root sum-of-squares of differences, and manhattan
- logical; if true, the measurements in
xare standardized before calculating the dissimilarities. Measurements are standardized for each variable (column), by subtracting the variable's mean value and dividing by the variable's me
pam is fully described in chapter 2 of Kaufman and Rousseeuw (1990).
Compared to the k-means approach in
kmeans, the function
the following features: (a) it also accepts a dissimilarity matrix;
(b) it is more robust because it minimizes a sum of dissimilarities
instead of a sum of squared euclidean distances; (c) it provides a novel
graphical display, the silhouette plot (see
which also allows to select the number of clusters.
pam-algorithm is based on the search for
k representative objects or
medoids among the observations of the dataset. These observations should
represent the structure of the data. After finding a set of
k clusters are constructed by assigning each observation to the nearest
medoid. The goal is to find
k representative objects which minimize the
sum of the dissimilarities of the observations to their closest representative
The algorithm first looks for a good initial set of medoids (this is called
the BUILD phase). Then it finds a local minimum for the objective function,
that is, a solution such that there is no single switch of an observation with
a medoid that will decrease the objective (this is called the SWAP phase).
- an object of class
"pam"representing the clustering. See
For datasets larger than (say) 200 observations,
pam will take a lot of
computation time. Then the function
clara is preferable.
## generate 25 objects, divided into 2 clusters. x <- rbind(cbind(rnorm(10,0,0.5), rnorm(10,0,0.5)), cbind(rnorm(15,5,0.5), rnorm(15,5,0.5))) pamx <- pam(x, 2) pamx summary(pamx) plot(pamx) pam(daisy(x, metric = "manhattan"), 2, diss = TRUE) data(ruspini) ## Plot similar to Figure 4 in Stryuf et al (1996) plot(pam(ruspini, 4), ask = TRUE) <testonly>plot(pam(ruspini, 4))</testonly>