chol2inv                package:base                R Documentation

_I_n_v_e_r_s_e _f_r_o_m _C_h_o_l_e_s_k_i (_o_r _Q_R) _D_e_c_o_m_p_o_s_i_t_i_o_n

_D_e_s_c_r_i_p_t_i_o_n:

     Invert a symmetric, positive definite square matrix from its
     Choleski decomposition.  Equivalently, compute (X'X)^(-1) from the
     (R part) of the QR decomposition of X.

_U_s_a_g_e:

     chol2inv(x, size = NCOL(x), LINPACK = FALSE)

_A_r_g_u_m_e_n_t_s:

       x: a matrix.  The first 'size' columns of the upper triangle
          contain the Choleski decomposition of the matrix to be
          inverted.

    size: the number of columns of 'x' containing the Choleski
          decomposition.

 LINPACK: logical.  Should LINPACK be used (for compatibility with R <
          1.7.0)?

_D_e_t_a_i_l_s:

     This is an interface to the LAPACK routine DPOTRI and the LINPACK
     routine DPODI.

_V_a_l_u_e:

     The inverse of the matrix whose Choleski decomposition was given.

_R_e_f_e_r_e_n_c_e_s:

     Dongarra, J. J., Bunch, J. R., Moler, C. B. and Stewart, G. W.
     (1978) _LINPACK Users Guide_. Philadelphia: SIAM Publications.

     Anderson. E. and ten others (1999) _LAPACK Users' Guide_. Third
     Edition. SIAM. Available on-line at <URL:
     http://www.netlib.org/lapack/lug/lapack_lug.html>.

_S_e_e _A_l_s_o:

     'chol', 'solve'.

_E_x_a_m_p_l_e_s:

     cma <- chol(ma  <- cbind(1, 1:3, c(1,3,7)))
     ma %*% chol2inv(cma)