rankindex               package:vegan               R Documentation

_C_o_m_p_a_r_e_s _D_i_s_s_i_m_i_l_a_r_i_t_y _I_n_d_i_c_e_s _f_o_r _G_r_a_d_i_e_n_t _D_e_t_e_c_t_i_o_n

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

     Rank correlations between dissimilarity indices and gradient
     separation.

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

     rankindex(grad, veg, indices = c("euc", "man", "gow", "bra", "kul"),
               stepacross = FALSE, method = "spearman", ...)

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

    grad: The gradient variable or matrix. 

     veg: The community data matrix. 

 indices: Dissimilarity indices compared, partial matches to
          alternatives in 'vegdist'.

stepacross: Use 'stepacross' to find a shorter path dissimilarity. The
          dissimilarities for site pairs with no shared species are set
          'NA' using 'no.shared' so that indices with no fixed upper
          limit can also be analysed.

  method: Correlation method used. 

     ...: Other parameters to 'stepacross'.

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

     A good dissimilarity index for multidimensional scaling  should
     have a high rank-order similarity with gradient separation. The
     function compares most indices in 'vegdist' against gradient
     separation using rank correlation coefficients in 'cor.test'.

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

     Returns a named vector of rank correlations.

_N_o_t_e:

     There are several problems in using rank correlation coefficients.
     Typically there are very many ties when n(n-1)/2 gradient
     separation values are derived from just n observations. Due to
     floating point arithmetics, many tied values differ by machine
     epsilon and are arbitrarily ranked differently by 'rank' used in
     'cor.test'.  Two indices which are identical with certain
     transformation or standardization may differ slightly (magnitude
     10^{-15}) and this may lead into third or fourth decimal
     instability in rank correlations.  Small differences in rank
     correlations should not be taken too seriously.  Probably this
     method should be replaced with a sounder method, but I do not yet
     know which...  You may experiment with 'mantel', 'anosim' or even
     'protest'.

     Earlier version of this function used 'method = "kendall"', but
     that is far too slow in large data sets.

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

     Jari Oksanen

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

     Faith, F.P., Minchin, P.R. and Belbin, L. (1987).  Compositional
     dissimilarity as a robust measure of ecological distance.
     _Vegetatio_ 69, 57-68.

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

     'vegdist', 'stepacross', 'no.shared', 'isoMDS', 'cor', 'Machine',
     and for alternatives 'anosim', 'mantel' and 'protest'.

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

     data(varespec)
     data(varechem)
     ## The next scales all environmental variables to unit variance.
     ## Some would use PCA transformation.
     rankindex(scale(varechem), varespec)
     rankindex(scale(varechem), wisconsin(varespec))

