VerbAgg                 package:lme4                 R Documentation

_V_e_r_b_a_l _A_g_g_r_e_s_s_i_o_n _i_t_e_m _r_e_s_p_o_n_s_e_s

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

     These are the item responses to a questionaire on verbal
     aggression. These data are used throughout De Boeck and Wilson,
     _Explanatory Item Response Models_ (Springer, 2004) to illustrate
     various forms of item response models.

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

     A data frame with 7584 observations on the following 13 variables.

     '_A_n_g_e_r' the subject's Trait Anger score as measured on the
          State-Trait Anger Expression Inventory (STAXI)

     '_G_e_n_d_e_r' the subject's gender - a factor with levels 'M' and 'F'

     '_i_t_e_m' the item on the questionaire, as a factor

     '_r_e_s_p' the subject's response to the item - an ordered factor with
          levels 'no' < 'perhaps' < 'yes'

     '_i_d' the subject identifier, as a factor

     '_b_t_y_p_e' behavior type - a factor with levels 'curse', 'scold' and
          'shout'

     '_s_i_t_u' situation type - a factor with levels 'other' and 'self'
          indicating other-to-blame and self-to-blame

     '_m_o_d_e' behavior mode - a factor with levels 'want' and 'do'

     '_r_2' dichotomous version of the response - a factor with levels
          'N' and 'Y'

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

     <URL: http://bear.soe.berkeley.edu/EIRM/>

_R_e_f_e_r_e_n_c_e_s:

     De Boeck and Wilson (2004), _Explanatory Item Response Models_,
     Springer.

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

     str(VerbAgg)
     xtabs(~ item + resp, VerbAgg)
     xtabs(~ btype + resp, VerbAgg)
     round(100 * ftable(prop.table(xtabs(~ situ + mode + resp, VerbAgg), 1:2), 1))
     person <- unique(subset(VerbAgg, select = c(id, Gender, Anger)))
     if (require(lattice)) {
         densityplot(~ Anger, person, groups = Gender, auto.key = list(columns = 2),
                     xlab = "Trait Anger score (STAXI)")
     }

