SortModes               package:mlica               R Documentation

_S_o_r_t_i_n_g _o_f _I_C_A _m_o_d_e_s

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

     Sorts inferred ICA modes using two criteria: Relative data power
     or the Liebermeister criterion, which is based on a measure that
     is a weighted linear combination of non-gaussianity and data
     variance measures.

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

     SortModes(a.best,c.val = 0.25)

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

  a.best: The output object of 'mlica'.

   c.val: A parameter to control the relative weight of the two
          measures when using the Liebermeister criterion. Should be
          between 0 (pure data variance measure) and 1 (pure
          non-gaussianity). 

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

     A list with components: 

  a.best: The output of 'mlica'.

     rdp: The relative data power values obtained for each independent
          component.

     lbm: The Liebermeister contrast value for each component.

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

     Andrew Teschendorff aet21@cam.ac.uk

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

_1 Hyvaerinen A., Karhunen J., and Oja E.: _Independent Component
     Analysis_, John Wiley and Sons, New York, (2001).

_2 Kreil D. and MacKay D. (2003): _Reproducibility Assessment of
     Independent Component Analysis of Expression Ratios from DNA
     microarrays_, Comparative and Functional Genomics *4* (3),300-317.

_3 Liebermeister W. (2002): _Linear Modes of gene expression determined
     by independent component analysis_, Bioinformatics *18*, no.1,
     51-60.

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

