detergent              package:multcomp              R Documentation

_D_e_t_e_r_g_e_n_t _D_u_r_a_b_i_l_i_t_y _D_a_t_a _S_e_t

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

     Detergent durability in a fractional design experiment; data set 
     taken from Westfall et al. (1999, p. 189). Balanced incomplete
     block design.

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

     data(detergent)

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

     This data frame contains the following variables

     _d_e_t_e_r_g_e_n_t detergent at 5 levels: 1 ... 5

     _b_l_o_c_k block at 10 levels: 1 ... 10

     _p_l_a_t_e_s Response variable: number of plates washed before  the foam
          disappears.

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

     See Westfall et al. (1999, p. 189)

_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(detergent)

     N <- rep(2, 5)

     # BIBD: prepare the contrast matrix = all-pair comparisons for 
     # the 5 levels of detergent

     C <- contrMat(N, type="Tukey")

     # adjusted p-values: either using the contrast matrix C
     summary(simtest(plates ~ block+detergent, data=detergent, whichf="detergent",
                     ttype="logical", cmatrix=C))

     # or, more easily, type="Tukey"
     summary(simtest(plates ~ detergent + block, data=detergent,
             whichf="detergent", type="Tukey", ttype="logical"))

