pension              package:robustbase              R Documentation

_P_e_n_s_i_o_n _F_u_n_d_s _D_a_t_a

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

     The total 1981 premium income of pension funds of Dutch firms, for
     18 Professional Branches, from de Wit (1982).

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

     data(pension)

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

     A data frame with 18 observations on the following 2 variables.

     '_I_n_c_o_m_e' Premium Income (in millions of guilders)

     '_R_e_s_e_r_v_e_s' Premium Reserves (in millions of guilders)

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

     P. J. Rousseeuw and A. M. Leroy (1987) _Robust Regression and
     Outlier Detection_; Wiley, p.76, table 13.

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

     data(pension)
     plot(pension)

     summary(lm.p  <-    lm(Reserves ~., data=pension))
     summary(lmR.p <- lmrob(Reserves ~., data=pension))
     summary(lts.p <- ltsReg(Reserves ~., data=pension))
     abline( lm.p)
     abline(lmR.p, col=2)
     abline(lts.p, col=2, lty=2)

     ## MM: "the" solution is much simpler:
     plot(pension, log = "xy")
     lm.lp  <-    lm(log(Reserves) ~ log(Income), data=pension)
     lmR.lp <- lmrob(log(Reserves) ~ log(Income), data=pension)
     plot(log(Reserves) ~ log(Income), data=pension)
     ## no difference between LS and robust:
     abline( lm.lp)
     abline(lmR.lp, col=2)

