prabinit              package:prabclus              R Documentation

_P_r_e_s_e_n_c_e-_a_b_s_e_n_c_e _m_a_t_r_i_x _i_n_i_t_i_a_l_i_z_a_t_i_o_n

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

     'prabinit' converts a matrix into an object of class 'prab'
     (presence-absence). The matrix may be read from a file or an
     R-object. It may be a 0-1 matrix or a matrix with non-negative
     entries from which the 0-1 matrix is to be generated. 'print.prab'
     is a print method for such objects.

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

     prabinit(file = NA, prabmatrix = NA, rows.are.species = TRUE,
     neighborhood = "none", distance = "kulczynski", toprab = FALSE, toprabp
     = 0.05, outc = 5.2)

     ## S3 method for class 'prab':
     print(x, ...)

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

    file: string. 0-1 matrix ASCII file (such as example dataset
          'kykladspecreg.dat') from which the matrix is read by
          'read.table'.

prabmatrix: matrix with non-negative entries. Either 'file' or
          'prabmatrix' should be 'NA'.

rows.are.species: logical. If 'TRUE', rows are interpreted as species
          and columns are interpreted as regions. In this case, rows
          and columns are interchanged by 'prabinit'.

neighborhood: A string or a list with a component for every region. The
          components are vectors of integers indicating neighboring
          regions. A region without neighbors (e.g., an island) should
          be assigned a vector 'numeric(0)'. If 'neighborhood' is a
          filename, it is attempted to read such a list from a file,
          where every row should correspond to one region (such as
          example dataset 'nb.dat'). If 'neighborhood="none"', all
          neighborhoods are set to 'numeric(0)'. The neighborhood is
          tested by 'nbtest'.

distance: '"kulczinsky"', '"jaccard"' or '"none"'. The distance measure
          between species to compute by 'prabinit'.

  toprab: logical. If 'TRUE', a presence-absence matrix is computed
          from the non-negative input matrix. "Absence", i.e., the
          entry 0, is chosen if the original entry is 0, or the
          original entry is both smaller than 'toprabp' times the sum
          of entries in the corresponding region and log(original
          entry) is considered to be a lower outlier compared with the
          other entries of the corresponding species (see 'outc').
          "Presence", i.e., the entry 1, thus means that the original
          entry is non-negligible w.r.t. the species or w.r.t. the
          region.

 toprabp: numerical between 0 and 1, see 'toprab'.

    outc: numerical. Tuning constant for the outlier identification
          associated with 'toprab=TRUE'. An entry smaller than
          'outc*mad' times the median is considered as a lower outlier.

       x: object of class 'prab'.

     ...: necessary for print method.

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

     An object of class 'prab', which is a list with components 

 distmat: distance matrix between species.

    prab: presence-absence matrix. Rows are regions, columns are
          species.

      nb: neighborhood list, see above.

regperspec: vector of the number of regions occupied by a species.

specperreg: vector of the number of species present in a region.

n.species: number of species.

n.regions: number of regions.

distance: string denoting the chosen distance measure.

 spatial: 'TRUE', if there is a specified neighborhood structure.

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

     Christian Hennig hennig@math.uni-hamburg.de <URL:
     http://www.math.uni-hamburg.de/home/hennig/>

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

     'read.table', 'jaccard', 'kulczynski', 'nbtest'

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

     # If you want to use your own ASCII data files, use
     # x <- prabinit(file="path/prabmatrixfile",
     # neighborhood="path/neighborhoodfile")
     data(kykladspecreg)
     # Note: If you do not use the installed package, replace this by
     # kykladspecreg <- read.table("(path/)kykladspecreg.dat")
     data(nb)
     # Note: If you do not use the installed package, replace this by
     # nb <- list()
     # for (i in 1:34)
     #   nb <- c(nb,list(scan(file="(path/)nb.dat",
     #                   skip=i-1,nlines=1)))
     prabinit(prabmatrix=kykladspecreg, neighborhood=nb)

