fwdmvRandomStart           package:Rfwdmv           R Documentation

_R_a_n_d_o_m _S_t_a_r_t_i_n_g _P_o_i_n_t_s _f_o_r _t_h_e _M_u_l_t_i_v_a_r_i_a_t_e _F_o_r_w_a_r_d _S_e_a_r_c_h

_D_e_s_c_r_i_p_t_i_o_n:

     Produces a forward plot of the trajectories of the minimum
     distance outside the subset for several multivariate forward
     searches.  Peaked trajectories are often indicative of clusters in
     the data.  The identify function can be used to highlight these
     trajectories in the plot and to obtain one or more starting
     subsets that are quite likely to reveal group structure in the
     data.

_U_s_a_g_e:

     fwdmvRandomStart(X, n.starts = 50, scaled = TRUE, plot.it = TRUE)

_A_r_g_u_m_e_n_t_s:

       X: a matrix or data frame containing the data.

n.starts: a positive integer specifying the number of random starting
          subsets.

  scaled: a logical flag.  If 'TRUE' scaled mahalanobis distances are
          used.

 plot.it: a logical flag.  If 'TRUE' the minimum distance outside the
          subset trajectories are plotted.

_D_e_t_a_i_l_s:

     It is necessary to store the object returned by this function in
     order to use the identify function.  Additionally, the plot method
     can be used to redraw the plot.

_V_a_l_u_e:

     A list with class 'fwdmvRandomStart' containing the following
     components:

  starts: a numeric matrix whose rows contain the randomly selected
          starting subsets.

  mpomat: a numeric matrix where each column contains the minimum
          distance outside the subset trajectory for a particular
          multivariate forward search.

plot.domain: a numeric vector containing the subset sizes used during
          the forward search.

_S_e_e _A_l_s_o:

     'fwdmv', 'identify.fwdmvRandomStart', 'plot.fwdmvRandomStart'

_E_x_a_m_p_l_e_s:

     data(bank.dat)
     bank.rfs <- fwdmvRandomStart(bank.dat)
     # use identify and plot on bank.rfs #

