Package: kmed 0.4.2

1. Introduction | 2. Distance Computation | 2.A. Numerical variables (distNumeric) | 2.A.1. Manhattan weighted by range (method = "mrw") | 2.A.2. squared Euclidean weighted by range (method = "ser") | 2.A.3. squared Euclidean weighted by squared range (method = "ser.2") | 2.A.4. squared Euclidean weighted by variance (method = "sev") | 2.A.5. squared Euclidean (method = "se") | 2.B. Binary or Categorical variables | 2.B.1. Simple matching (matching) | 2.B.2. Co-occurrence distance (cooccur) | 2.C. Mixed variables (distmix) | 2.C.1 Gower (method = "gower") | 2.C.2 Wishart (method = "wishart") | 2.C.3 Podani (method = "podani") | 2.C.4 Huang (method = "huang") | 2.C.5 Harikumar and PV (method = "harikumar") | 2.C.6 Ahmad and Dey (method = "ahmad") | 3. K-medoids algorithms | 3.A. Simple and fast k-medoids algorithm (fastkmed) | 3.B. K-medoids algorithm | 3.C. Rank k-medoids algorithm (rankkmed) | 3.D. Increasing number of clusters k-medoids algorithm (inckmed) | 3.E. Simple k-medoids algorithm (skm) | 4. Cluster validation | 4.A. Internal criteria | 4.A.1. Silhouette (sil) | 4.A.2. Centroid-based shadow value (csv) | 4.A.3. Medoid-based shadow value (msv) | 4.B. Relative criteria | Step 1 Creating a matrix of bootstrap replicates | Step 2 Transforming the bootstrap matrix into a consensus matrix | Step 3 Visualizing the consensus matrix in a heatmap | 5. Cluster visualization | A. Biplot | B. Marked barplot | References