DutchPolitics              package:cmm              R Documentation

_P_o_l_i_t_i_c_a_l _p_a_r_t_y _a_n_d _c_a_n_d_i_d_a_t_e _p_r_e_f_e_r_e_n_c_e _i_n _t_h_e _N_e_t_h_e_r_l_a_n_d_s

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

     The data come from a Dutch panel study (T1 = February 1977, T2 =
     March 1977) and concern the questions for which party the
     respondent intends to vote (variables A and B, respectively) and
     which candidate the respondent prefers to become the next Prime
     Minister (C and D). The data have been analyzed before (Hagenaars,
     1986, 1988, 1990), and more information on the panel study and the
     outcomes may be obtained from these references.

     The data are tabulated in Bergsma, Croon, and Hagenaars (2009,
     Table 6.1).

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

     data(DutchPolitics)

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

     A data frame with 1100 observations on the following variables.

     '_A' Party preference at time 1 (factor): 1 = Christian Democrats;
          2 = Left wing; 3 = Other.

     '_B' Party preference at time 2 (factor): 1 = Christian Democrats;
          2 = Left wing; 3 = Other.

     '_C' Candidate preference at time 1 (factor): 1 = Christian
          Democrats; 2 = Left wing; 3 = Other.

     '_D' Candidate preference at time 2 (factor): 1 = Christian
          Democrats; 2 = Left wing; 3 = Other.


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

     J. A. Hagenaars (1990). _Categorical longitudinal data:
     log-linear, panel, trend, and cohort analysis_. Newbury Park: Sage

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

     Bergsma, W. P., Croon, M. A., & Hagenaars, J. A. P. (2009).
     _Marginal models for dependent, clustered, and longitudinal
     categorical data._ Berlin: Springer

     J. A. Hagenaars (1990). _Categorical longitudinal data:
     log-linear, panel, trend, and cohort analysis_. Newbury Park: Sage

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

     data(DutchPolitics)

     # Marginal homogeneity: A=C and B=D
     at2a <- MarginalMatrix(c("A","B","C","D"), list(c("A"), c("C")), c(3, 3, 3, 3));
     at2b <- MarginalMatrix(c("A","B","C","D"), list(c("B"), c("D")), c(3, 3, 3, 3));
     bt2 <- ConstraintMatrix(c(1,2), list(c(1),c(2)), c(2,3));
     at2 <- rbind(at2a, at2b);
     bt2 <- DirectSum(bt2, bt2);

     model <- list(bt2, "identity", at2);

     mpolMH <- MarginalModelFit(DutchPolitics, model,
         MaxError = 10.^-25,
         MaxSteps = 200,
         MaxStepSize = .5,
         StartingPoint = "Automatic",
         CoefficientDimensions = c(2, 2, 3),
         ShowProgress = 50);

