Encounter history data base

questions concerning analysis/theory using program MARK

Encounter history data base

Postby willyr » Tue Jun 06, 2006 4:44 am

I'm working on a fish population model and obviously use Mark to estimate my life parameters. I'm trying to wrote in Microsoft Access a data base in which you just have to input your original data individual xxxx caught in dd/mm/yyyy, and it will give automatically encounter history with corresponding numbers of individuals. I have some special constraints in my data, so I must made it in my own (same codes need to be check maénually).
So all this to ask if someone heard about this kind of things, to give me a base for my work.
Thanks, waiting for your answers

Willy Raub
willyr
 
Posts: 1
Joined: Mon May 29, 2006 10:43 am

creating encounter histories from a database

Postby ganghis » Tue Jun 06, 2006 10:05 am

Hi Willy,

Most statistical packages include data input/output and manipulation tools, at varying levels. SAS is probably the most efficient way to go, and can easily handle Access databases but of course involves using a somewhat counter-intuitive programming framework. Unfortunately, there is no general code available because of variability in the way people format their databases and the variability in forms of encounter histories.

Cheers, Paul Conn
ganghis
 
Posts: 84
Joined: Tue Aug 10, 2004 2:05 pm

Access - MARK

Postby jlaake » Tue Jun 06, 2006 12:48 pm

I have done what you are suggesting although my setup is unique to the data that I have but I can describe the process. It is quite straightforward to use the crosstab query in Access to do what you want. If you do a crosstab of animal id (rows) by capture date (columns) it will give you the beginning of what you want. You can then construct another query which uses the crosstab query to concatenate the 0/1 columns into a single capture history field and attach any covariates/grouping variables. Note that if you have more than one record of an animal on the same date then you need to include iif statements to convert any non-zero count to 1. If you have groups, you could then construct a third query from the second query which is a crosstab of capture history by group variables if you don't have any individual covariates. If you have groups and individual covariates, then construct the third query as a crosstab of animal id by group variables and include the capture history and individual covariates as row values. Note that the crosstab wizard has limited flexibility but you can do many more things with crosstabs using the design mode.

Hope this helps --jeff
jlaake
 
Posts: 1480
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA


Return to analysis help

Who is online

Users browsing this forum: No registered users and 1 guest

cron