missingProjector        package:compositions        R Documentation

_R_e_t_u_r_n_s _a _p_r_o_j_e_c_t_o_r _t_h_e _t_h_e _o_b_s_e_r_v_e_d _s_p_a_c_e _i_n _c_a_s_e _o_f _m_i_s_s_i_n_g_s.

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

     Returns projectors on the observed subspace in the presence of
     missings.

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

     missingProjector(x,...,by="s")
     ## S3 method for class 'acomp':
     missingProjector(x,has=is.NMV(x),...,by="s")
     ## S3 method for class 'aplus':
     missingProjector(x,has=is.NMV(x),...,by="s")
     ## S3 method for class 'rcomp':
     missingProjector(x,has=!(is.MAR(x)|is.MNAR(x)),...,by="s")
     ## S3 method for class 'rplus':
     missingProjector(x,has=!(is.MAR(x)|is.MNAR(x)),...,by="s")

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

       x: a dataset or object of the given class

     has: a boolean matrix of the same size indicating nonmissing
          values

     ...: additional arguments for generic purpose only

      by: the name of the dataset dimension on 'has' for tensorial
          computation with tensorA package

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

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

     A dataset of N square matrices of dimension DxD (with N and D
     respectively  equal to the number of rows and columns in 'x').
     Each of these  matrices gives the projection of a data row onto
     its observed sub-space. 
      The function 'sumMissingProjector' takes all these matrices and
     sums them, generating a "summary" of observed sub-spaces. This
     matrix is useful to obtain estimates of the mean (and variance, in
     the future) still unbiased  in the presence of lost values (only
     of type MAR, stricly-speaking, but anyway useful for any type of
     missing value, when used with care).

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

     K.G.van den Boogaart

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

     Boogaart, K.G. v.d. (2006) Concepts for handling of zeros and
     missing values in compositional data, in E. Pirard (ed.)
     (2006)Proccedings of the IAMG'2006 Annual Conference on
     "Quantitative Geology from multiple sources", September 2006,
     Liege, Belgium, S07-01, 4pages, <URL:
     http://www.math-inf.uni-greifswald.de/~boogaart/Publications/iamg0
     6_s07_01.pdf>

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

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

     data(SimulatedAmounts)
     x <- acomp(sa.lognormals)
     xnew <- simulateMissings(x,detectionlimit=0.05,MAR=0.05,MNAR=0.05,SZ=0.05)
     xnew
     plot(missingSummary(xnew))

     missingProjector(acomp(xnew))
     missingProjector(rcomp(xnew))
     missingProjector(aplus(xnew))
     missingProjector(rplus(xnew))

