Fairly major upgrade, from 3.2 -> 4.0.
While the new build fixes a number of 'small irritations', the two main changes are:
1. The capability to run multiple multiple models simultaneously has been re-instituted into the program, no matter what operating system is being used. Thus, you can start the numerical optimization of a model, and then begin preparing and then start of the optimization of additional models while the first one continues to execute.
Some of you may recall that multi-threaded operations in previous versions of MARK were pretty weel-guaranteed to make your system crash and burn. There were several workarounds, the most useful of which was to build and save the individual models, then run them all as a 'batch' job.
97. Markov Chain Monte Carlo (MCMC) estimation for all data types is now implemented, mainly to provide increased capability for estimation of variance components. However, the code is for this estimation procedure is aimed primarily at modeling the beta parameters for models constructed with the logit link function, although inputs can be provided to accommodate other link functions for specific data types, such as the log link for population estimates (N). The one or more hyperdistributions being modeled are thus generally on the logit scale. However, considerably flexibility has been provided to model the hyperdistributions, including a design matrix on the means and a full variance-covariance matrix to estimate process covariances (actually correlations). MCMC estimation is obtained by checking the MCMC check box in the Run Window. Typically the parameter estimates from the ML procedure would be used as the initial parameter values for the MCMC procedure to ensure that the Markov Chain is started at reasonable values. Output is displayed in a NotePad Window, consisting of the mean, standard deviation, mode, and median of the posterior distribution, plus the 2.5, 5, 10, 20, 80, 90, 95, and 97.5 percentiles. Note that no output is stored in the Results Browser. In addition, a binary file of the sample from the posterior distribution is provided, along with example SAS code in the help file for reading and summarizing this sample. Full details on the MCMC estimation procedure are provided in the MARK help file.
You can download the latest version of MARK, either from Gary's site, or here at
http://www.phidot.org/software/mark/download