| LaborParticipation {cmm} | R Documentation |
The labor participation (yes/no) of 1583 women was measured in five consecutive year, 1967-1971, leading to a 2 x 2 x 2 x 2 x 2 table.
The data are tabulated in Bergsma, Croon, and Hagenaars (2009, p. 128).
Section 4.3 in Bergsma, Croon and Hagenaars, 2009
data(LaborParticipation)
A data frame with 1583 observations on the following variables.
Year1967Year1968Year1969Year1970Year1971Heckman & Willis (1977).
Bergsma, W. P., Croon, M. A., & Hagenaars, J. A. P. (2009). Marginal models for dependent, clustered, and longitudinal categorical data. New York: Springer.
Heckman, J. J. & Willis, R. J. (1977). A beta-logistic model for the analysis of sequential labor force participation by married women. Journal of Political Economy, 85, 27-58.
data(LaborParticipation)
n <- c(t(ftable(LaborParticipation)))
##############################################################################################################
#Sample kappa values
#matrix for obtaining transition matrices for consecutive years
at = MarginalMatrix(c("67","68","69","70","71"),list(c("67","68"),c("68","69"),c("69","70"),c("70","71")),c(2,2,2,2,2));
coeff = SpecifyCoefficient("CohenKappa",2,4);
SampleStatistics(n,list(coeff,at),ShowParameters=FALSE)
##############################################################################################################
#Fitting models for kappa
#matrix for obtaining transition matrices for consecutive years
at = MarginalMatrix(c("67","68","69","70","71"),list(c("67","68"),c("68","69"),c("69","70"),c("70","71")),c(2,2,2,2,2));
coeff = SpecifyCoefficient("CohenKappa",2,4);
bt1 = ConstraintMatrix(c(1),c(),c(4)); #equal kappas
bt2 = rbind(c(1,-2,1,0),c(0,1,-2,1)); #linear trend for kappas
model = list(bt1,coeff,at)
m=MarginalModelFit(n,model,ShowParameters=FALSE,ShowProgress=10)