litter               package:multcomp               R Documentation

_L_i_t_t_e_r _W_e_i_g_h_t_s _D_a_t_a _S_e_t

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

     Dose response of litter weights in rats; data set taken from
     Westfall et al. (1999, p. 109). Specific dose comparisons in a
     dose response experiment with two covariates.

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

     data(litter)

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

     This data frame contains the following variables

     _d_o_s_e Dosages at 4 levels: '0', '5', '50',  '500'.

     _g_e_s_t_t_i_m_e Gestation time as covariate.

     _n_u_m_b_e_r Number of animals in litter as covariate.

     _w_e_i_g_h_t Response variable: average post-birth weights  in the
          entire litter.

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

     See Westfall et al. (1999, p. 109)

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

     P. H. Westfall, R. D. Tobias, D. Rom, R. D. Wolfinger, Y. Hochberg
     (1999). _Multiple Comparisons and Multiple Tests Using the SAS
     System_. Cary, NC: SAS Institute Inc.

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

     data(litter)

     # define the contrast matrix, either completly
     C <- matrix(c(0,0,0,0,0,0,1,1,1,.75,.384,.887,-1,0,0,.25,.37,.113,
            0,-1,0,-.25,.246,-.339,0,0,-1,-.75,-1,-.661,0,0,0,
            0,0,0,0,0,0,0,0,0), ncol=7)
     # numerate the contrasts
     rownames(C) <- paste("C", 1:nrow(C), sep="")

     # simultaneous confidence intervals for above comparisons 
     # in an ANCOVA
     summary(simint(weight ~ dose + gesttime + number, data=litter,
                    alternative="greater", cmatrix=C))

     # or for dose only
     D <- matrix(c(1,1,1,.75,.384,.887,-1,0,0,.25,.37,.113,0,-1,0,-.25,
                   .246,-.339,0,0,-1,-.75,-1,-.661),ncol = 4)
     rownames(D) <- paste("D", 1:nrow(D), sep="")

     summary(simint(weight ~ dose + gesttime + number, data=litter,
                    whichf="dose", alternative="greater", cmatrix=D))

