VEM                  package:Icens                  R Documentation

_C_o_m_p_u_t_e _t_h_e _N_P_M_L_E _o_f _p _v_i_a _t_h_e _V_e_r_t_e_x _E_x_c_h_a_n_g_e _M_e_t_h_o_d.

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

     The Vertex Exchange Method is used to obtain the NPMLE of 'p'.

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

     VEM(A, pvec, maxiter=500, tol=1e-07, tolbis=1e-07, keepiter=FALSE)

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

       A: The m by n incidence matrix or the n by 2 matrix of
          intervals. 

    pvec: The initial estimate for the probability vector. 

 maxiter: The maximum number of iterations allowed. 

     tol: The tolerance used to determine convergence. 

  tolbis: The tolerance used in the bisection stage of the algorithm. 

keepiter: Should iteration information be retained and returned.

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

     Lots.

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

     An object of class 'icsurv' with the following components. 

     pf : The NPMLE of the probability vector. 

numiter : The number of iterations used.

    lval: The value of the logarithm of the likelihood at the NPMLE. 

converge: Boolean stating whether the iteration converged.

  intmap: If present it contains the real representations for the
          maximimal cliques. These are the intervals (on the real line)
          where the mass in 'pf' is placed.

_A_u_t_h_o_r(_s):

     Robert Gentleman and Alain Vandal

_R_e_f_e_r_e_n_c_e_s:

     _A Vertex-exchange-method in $D$-optimal Design Theory _, D.
     Bohning, Metrika, 1986.

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

     'EM', 'ISDM', 'EMICM', 'PGM'

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

         data(cosmesis)
         csub1 <- subset(cosmesis, subset=Trt==0, select=c(L,R))
         VEM(csub1)
         data(pruitt)
         VEM(pruitt)

