

_C_o_v_a_r_i_a_n_c_e _M_a_t_r_i_c_e_s

     var(x, y=x, na.rm=FALSE, use)

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

       x: a matrix or vector.

       y: a matrix or vector.

   na.rm: logical.

     use: an optional character string giving a method for
          computing covariances in the presence of missing
          values.  This must be one of `"all.obs"',
          `"complete.obs"' or `"pairwise.complete.obs"',
          with abbreviation being permitted.

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

     `var' computes the variance of `x' and the covariance
     of `x' and `y' if `x' and `y' are vectors.  If `x' and
     `y' are matrices then the covariance between the
     columns of `x' and the the columns of `y' are computed.

     If `na.rm' is `TRUE' then the complete observations
     (rows) are use to compute the variance.  If `na.rm' is
     `FALSE' and there are missing values, then `var' will
     fail.

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

     The argument `use' can also be used for describing how
     to handle missing values.  Specifying `use="all"' is
     equivalent to specifying `na.rm=FALSE' and specifying
     `use="pair"' is equivalent to `na.rm=TRUE'.  If
     `use="pair"', then all the observations which are com-
     plete for a pair of variables are used to compute the
     covariance for that pair of variables.  This can result
     in covariance matrices which are not positive semide-
     finite.

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

     `cov' with the same functionality for the multivariate
     case.

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

     var(1:10)# 9.166667

     var(1:5,1:5)# 2.5

