Create a control structure for running EM algorithms

em.control(ctrl = NULL, ...)

Arguments

nplot how often to plot wages of comparaison to model0 how often to log information maximum number of iterations whether to allow for flexible variance (default is TRUE) TBD defines the type of constraints on the means for estimation TBD tolerance for stopping the EM posterior likelihood to use instead of computing them using initial parameters model to compare estimation to when plotting TBD setting a particular weight for stayers versus movers (default is 1) vector of TRUE/FALSE that states which rho should be estimated whether to estimate rho in level of in differences Dirichlet prior for proportions (default 1.01) number firms to update in probabilistic approach what terms to include in the liklihood for probabilistic approach (default to = c(1,1,1,1)) whether to check the likelihood at each updating parameter whether to use stochastic EM instead of straight EM when TRUE, imposes fixed interactions in different time periods when TRUE, levels are not updated, only variances and proportions TBD TBD floor imposed on all standard deviations (default is 1e-10) term added to posterior probablities (this is to deal with numerical issues, default is 1e-9) text to show in logging share of the stayers to use in estimation whether to redraw the subsample of stayers size to use in simulation weight attributed to stayers in joint estimation number of starting values for EM number of best starting values to select from using connectedness