new MARK build - April 10, 2004

announcements (new versions, changes, bugs, installation problems...) related to program MARK

new MARK build - April 10, 2004

Postby cooch » Tue Apr 13, 2004 9:24 pm

Gary has released a new build of MARK, which has several new features which are of sufficient note that it is probably worth downloading and installing the newest version (which you can get from http://www.phidot.org/software/mark/download ). Here are the most notable changes:

:arrow: The derived parameters from the Huggins models (population size) can now be used in model averaging and variance components. Huggins models can be used with closed capture data, robust-design data, and robust-design multi-strata data. For robust-design multi-strata data, a population estimate is generated for each strata at each primary occasion. To allow derived parameters to be used in the model averaging and variance components analyses, the variance-covariance matrix of the derived parameters must be computed, and so this matrix is also available in either a notepad window or else an Excel spreadsheet.

:arrow: For all of the multi-strata data types, including the robust-design multi-strata models, the transition probability (psi) obtained by subtraction can be selected with the Change PIM definitions menu choice. Previously, the default value of psi was the probability of remaining in the strata (e.g., psi A to A). Now, the user can select the transition probability to obtain by subtraction. This change allows fixing the probability of remaining in the strata to zero, a model that was not possible in the previous versions of MARK. One problem with this change is that care must be taken to only model average parameter values for psi PIMs that share the same definition. More details on this capability can be found in the MARK help file.

:arrow: A new method of estimating the overdispersion parameter, c, has been implemented with the Median chat menu choice. The approach is to simulate data for a range of c values, and perform a logistic regression to estimate the value of c for which the probability of obtaining a deviance c-hat greater than the observed deviance c-hat is 0.5. More details on this procedure can be found in the MARK help file.

In particular, the most interesting new feature (for most users) will be the third item. As you know, handling GOF issues is the biggest challenge we often face. A new approach to this pernicious little problem is always welcome.
cooch
 
Posts: 1628
Joined: Thu May 15, 2003 4:11 pm
Location: Cornell University

Return to software problems/news

Who is online

Users browsing this forum: No registered users and 12 guests