Mississippi             package:SASmixed             R Documentation

_N_i_t_r_o_g_e_n _c_o_n_c_e_n_t_r_a_t_i_o_n_s _i_n _t_h_e _M_i_s_s_i_s_s_i_p_p_i _R_i_v_e_r

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

     The 'Mississippi' data frame has 37 rows and 3 columns.

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

     This data frame contains the following columns:

     _i_n_f_l_u_e_n_t an ordered factor with levels '3' < '5' < '2' < '1' < '4'
          < '6'

     _y a numeric vector

     _T_y_p_e a factor with levels '1'  '2'  '3' 

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

     Littel, R. C., Milliken, G. A., Stroup, W. W., and Wolfinger, R.
     D. (1996), _SAS System for Mixed Models_, SAS Institute (Data Set
     4.2).

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

     options(
       contrasts = c(unordered = "contr.SAS", ordered = "contr.poly"))
     data(Mississippi)
     formula( Mississippi )
     #plot( Mississippi )
     fm1Miss <- lme( y ~ 1, data = Mississippi, random = ~ 1 | influent )
     summary( fm1Miss )        # compare with output 4.1, p. 142
     fm1MLMiss <- update( fm1Miss, method = "ML" )
     summary( fm1MLMiss )        # compare with output 4.2, p. 143
     random.effects( fm1MLMiss ) # BLUP's of random effects on p. 144
     random.effects( fm1MLMiss , aug = TRUE )   # including covariates
     random.effects( fm1Miss )   # BLUP's of random effects on p. 142
     intervals( fm1Miss )        # interval estimates of variance components
     VarCorr( fm1Miss )          # compare to output 4.7, p. 148
     fm2Miss <- lme( y ~ Type, data = Mississippi, random = ~ 1 | influent,
           method = "REML" )
     summary( fm2Miss )         # compare to output 4.8 and 4.9, pp. 150-152
     anova( fm2Miss )

