Hello, I would consider a removal model instead. Unless you have a small population of roaches, it will be challenging to mark enough individuals to compute a reasonable population estimate. I think you'll end up with a population estimate of something akin to N(hat) = 600, 95% CI: 240 to 12,000.
Acknowledging Malcolm's concern about angering higher-ups, a removal model would actually result in a population reduction because you would squash each cockroach when you "remove" it from the population at each sampling interval. So you'll be teaching ecology and performing pest control! To get a reasonable population estimate with a removal model, though, you will need to remove a substantial portion of the population on each 'pass' (i.e., a downward trend in the number of roaches "captured" each time) or you'll have the same troubles as mentioned above for the mark-recap (actually mark-resight in your example). Why not do both. Have one set of dorms do a mark-resight experiment and the other set of dorms complete a removal experiment. You won't be able to compare the accuracy of the two estimators (since you'll be estimating two different populations), but you'll expose the students to two types of models and expose them to the uncertainty that goes into designing an experiment with wild organisms. Jason On Sun, Jul 15, 2012 05:31 PM "=?ISO-8859-1?Q?Brett_A._McMillan?=" <[email protected]> wrote: > >I was thinking of having students do a mark-recapture population size estimation of the cockroaches >in their dorms for my intro ecology class. Anyone ever try this for a class (or otherwise) and have any >advice (say about the best marking technique)? >Thanks! > > 'Nothing in biology makes sense, except in the light of evolution' --Theodosius Dobzhansky-- Jason Hill www.coopunits.org/Pennsylvania/People/Jason_Hill/index.html PA Cooperative Fish and Wildlife Research Unit 221 Forest Resources Building University Park, PA 16802-4705 Office: 814-865-0772 Fax: 814-863-4710 Ecology Program - PhD Candidate Pennsylvania State University School of Forest Resources
