Nonmetric MDS with isotonic regression

Kruskal-style nonmetric MDS using pool-adjacent-violators monotone regression on dissimilarity ranks.

Usage

morie_spatial_voting_nonmetric_mds(
  D,
  n_dims = 2L,
  max_iter = 300L,
  tol = 1e-06
)

Arguments

D

Symmetric dissimilarity matrix.

n_dims

Number of dimensions.

max_iter

Maximum iterations.

tol

Convergence tolerance.

Value

A list with coordinates, stress, iterations, converged.

References

Kruskal, J. B. (1964). "Nonmetric Multidimensional Scaling: A Numerical Method." Psychometrika, 29(2), 115-129.

Examples

set.seed(1)
D <- as.matrix(dist(matrix(rnorm(40), 10)))
morie_spatial_voting_nonmetric_mds(D)
#> $coordinates
#>                [,1]          [,2]
#>  [1,] -0.0031223833  0.0019648108
#>  [2,] -0.0006239853  0.0016124854
#>  [3,] -0.0018900064 -0.0006529608
#>  [4,]  0.0058992574 -0.0050639355
#>  [5,]  0.0008861369  0.0023563786
#>  [6,] -0.0003426374  0.0007903518
#>  [7,]  0.0007064778  0.0001367434
#>  [8,]  0.0012126972 -0.0014879207
#>  [9,] -0.0010592770 -0.0004019061
#> [10,] -0.0016662799  0.0007459531
#> 
#> $stress
#> [1] 0.09649346
#> 
#> $iterations
#> [1] 300
#> 
#> $converged
#> [1] FALSE
#>