| PRTools contents |
MDS_INIT
Y = MDS_INIT (D,N,INIT)
| Input | |
| D | Square dissimilarity matrix of the size M x M |
| N | Desired output dimensionality (optional; default: 2) |
| INIT | Initialization method (optional; default: 'randnp') |
| Output | |
| Y | Initial configuration for the MDS method |
Finds a configuration of points Y in an N-dimensional space, used as a starting configuration for an MDS mapping based on the distance matrix D. The parameter INIT is a string standing for the initialization method
'randp' - linear mapping of D on n randomly (uniform distribution) chosen vectors 'randnp' - linear mapping of D on n randomly (normal distribution) chosen vectors 'randv' - randomly (uniform distribution) chosen vectors from D 'maxv' - n columns of D with the largest variances 'kl' - Karhunen Loeve projection (linear mapping) of D (first n eigenvectors) 'cs' - Classical Scaling
| PRTools contents |