vanbelle1Fit function

survivalsvm (ranking approach)

fits the 'vanbelle1' version of the ranking approach of survival support vector ananlysis.

vanbelle1Fit(
  X,
  Y,
  delta,
  meth_par = 1,
  kernel_type = "lin_kernel",
  kernel_pars = NA,
  bin_cat = integer(0),
  makediff = makediff3,
  opt_alg = "quadprog",
  sgf_sv = 5,
  sigf = 7,
  maxiter = 40,
  margin = 0.05,
  bound = 10,
  eig.tol = 1e-06,
  conv.tol = 1e-07,
  posd.tol = 1e-08
)

Arguments

• X: [matrix(1)]

  Matrix of training data points.

• Y: [vector(1)]

  Vector of survival times.

• delta: [vector(1)]

  Vector of status: 1 = not censored.

• meth_par: [numeric(1)]

  Parameter of regularization.

• kernel_type: [character(1)]

  Kernel that will be used to fit the model. The handled type are: linear kern ('lin_kern'), additive kernel ('add_kernel'), radial basis kernels ('rbf_kernel' and 'rbf4_kernel') and the polynomial kernel ('poly_kernel').

• kernel_pars: [numeric(1)|vector(1)]

  Parameters of kernel, when required.

• bin_cat: [vector(1)]

  Indexes of binary/categorical varibales

• makediff: [character(1)]

  String indicating which of 'makediff1', 'makediff2' or 'makediff3'

  will be used.

• opt_alg: [vector(1)]

  Program that will be used to solve the quadratic optimization problem. Either quadprog or ipop.

• sgf_sv: [integer(1)]

  Number of decimal digits in the solution of the quadratic optimization problem.

• sigf: [integer(1)]

  Used by ipop. See ipop for details.

• maxiter: [integer(1)]

  Used by ipop. See ipop for details.

• margin: [numeric(1)]

  Used by ipop. See ipop for details.

• bound: [numeric(1)]

  Used by ipop. See ipop for details.

• eig.tol: [numeric(1)]

  Used by nearPD for adjusting positive definiteness. See nearPD for detail.

• conv.tol: [numeric(1)]

  Used by nearPD for adjusting positive definiteness. See nearPD for detail.

• posd.tol: [numeric(1)]

  Used by nearPD for adjusting positive definiteness. See nearPD for detail.

Returns

[VB1FitObj(1)] object of class VB1FitObj containing elements:

Alpha	solution of the quadratic optimization problem,
Xtrain	matrix of training data points,
DifMat	matrix used to maked differences between neighbor points,
Kernel	kernel matrix, an object of class Kernel ,
OptMeth	program used to solve the quadratic optimization problem.

Author(s)

Cesaire J. K. Fouodo