brain                 package:rrcov                 R Documentation

_B_r_a_i_n _a_n_d _B_o_d_y _W_e_i_g_h_t_s _f_o_r _2_8 _S_p_e_c_i_e_s

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

     Average brain and body weights for 28 species of land animals.  If
     the log of the two variables, i.e. log(brain weight) and  log(body
     weight) are taken, the classical Mahalanobis distance  declares
     only observation 25 (Brachiosaurus) as an outlier,  whereas the
     robust distances computed using for example MCD -  covMcd() -
     declare four observations as outliers (25, 6, 14 and 16).  These
     are three dinosaurs with relatively small brains and the  human
     with relatively heavy brain.

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

     data(brain)

_F_o_r_m_a_t:

     A data frame with 28 observations on the following 2 variables.

     '_b_o_d_y' body weight in kg

     '_b_r_a_i_n' brain weight in g

_N_o_t_e:

     This data set is also available in the package MASS under the name
     'Animals', but the observations 25 (Brachiosaurus) and 26 (Rat)
     are swaped.

_S_o_u_r_c_e:

     P. J. Rousseeuw and A. M. Leroy (1987)  _Robust Regression and
     Outlier Detection._ Wiley, p.57.

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

     data(brain)
     lbrain<-log(brain)
     plot(mahalanobis(lbrain,mean(lbrain),var(lbrain)))

     mcd<-covMcd(lbrain)
     plot(mahalanobis(lbrain,mcd$center,mcd$cov))

