[Ipmpack-users] Outliers in an IPM

[IVAN ALEJANDRO ORTIZ]

Hello everyone,

I’m writing to request your help/opinion. I’m constructing an stochastic IPM for an orchid in Cuba. We measure the foliar  area as our size variable during 6 yrs and we found a lot of individuals with size < 200 cm2, however there are 1 or 2 individuals each year whose foliar area is > 400 cm2, i.e. outliers. What should I do with this extreme data? Should I make an outlier analysis and forget the outliers to run glms? if so what kind of analysis is recommended? Should I consider the outliers in the glms but not in the kernel?, Should I consider all data?. 

On the other hand, once I have the IPMs for each year the function stochGrowthRateSampleList will help me to obtain the stochastic lambda? and what functions do you recommended to obtain sensitivity analysis?


Thanks to all for any suggestion,

Best wishes,

Elena Sulis



MSc. Iván Alejandro Ortiz-Rodríguez
Lab. de Ecología de Poblaciones y Comunidades Tropicales
Centro de Investigaciones en Ecosistemas, UNAM Campus Morelia

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/ipmpack-users/attachments/20150313/4463f8e9/attachment.html>