[Ipmpack-users] help with IPMpack

[Elena S.]

Good morning IPMusers,

thank you Dr. Jongejans for answered me so quickly, and sorry for my delay in answered you.

I use popbio with matrices, so I think it is not the best solution for IPMs (but remain A solution). However, I'm not actually able to create my own function, I will study more.

About Dr. Kendall's solution, I'm searching other methods to help me with my resampling of each year of data, because it is my first time with this type of analyses. Maybe the package "boot" can do the bootstrapping? Is that package correct to follow also the first suggestion of Joachim Topper?

Hence, at the moment, I'll study the resampling/bootstrapping methods and I'll wait for other solutions, if exists, so I thanks to all for your suggestion, I agree with Dr. Jongejans and I hope that others IPMusers share with me any possible idea for resolve my problem.

Elena

_________________________________________________________
Dott.ssa Elena Sulis, PhD
Centro Conservazione Biodiversità (CCB)
Sezione Botanica - Dipartimento di Scienze della Vita e dell'Ambiente (DISVA)
Università degli Studi di Cagliari (Italia)
E-mail: elenasulis at hotmail.it
Skype: elena.sulis


________________________________
Subject: Re: [Ipmpack-users] help with IPMpack
To: elenasulis at hotmail.it; ipmpack-users at lists.r-forge.r-project.org
From: e.jongejans at science.ru.nl
Date: Wed, 27 Jul 2016 11:23:35 +0200

Dear Elena,
the function stochGrowthRateSampleList only returns the mean of the per-time-step population growth rates in a stochastic simulation. If you want to know the distribution of these per-time-step population growth rates you could write your own version of this function and make sure that that distribution is stored as well. On the other hand if you want a CI for the resulting mean stochastic population growth rate, you code write code in which stochGrowthRateSampleList is called multiple times, and analyse the resulting distribution of mean stochastic population growth rates. If other people have other solutions, please share them!

Please also note the description of the stochGrowthRateSampleList function, that reads "Note that the function stoch.growth.rate in the package popbio does this more efficiently and with more useful output; but may fail for large bin numbers.".

I hope this helps,
Eelke




On 20-Jul-16 1:48 PM, Elena S. wrote:

Hi,

I try to calculate CI (confidence intervals) for my stochastic population growth rate. I started with 4 IPM (four years of study), then I run the following function:

exp(stochGrowthRateSampleList(list(IPM9,IPM10,IPM11,IPM12),nRunIn = 100, tMax = 5000))

or the following ones, based on the IPMpack manual (Metcalf et al. 2014):

exp(stochGrowthRateSampleList(nRunIn=100,tMax=5000,listIPMmatrix=list(IPM9,IPM10,IPM11,IPM12),
                              listPmatrix=list(Pmatrix9,Pmatrix10,Pmatrix11,Pmatrix12),
                              listFmatrix=list(Fmatrix9,Fmatrix10,Fmatrix11,Fmatrix12),
                              seedList=NULL,
                              densDep=FALSE))

and I obtained a stochastic lambda of 1.25, but, at the moment, I don't know how to calculate the confidence intervals.

Anyone can help me?

Thanks in advance,

best regards,

Elena



_________________________________________________________
Dott.ssa Elena Sulis, PhD
Centro Conservazione Biodiversità (CCB)
Sezione Botanica - Dipartimento di Scienze della Vita e dell'Ambiente (DISVA)
Università degli Studi di Cagliari
V.le Sant'Ignazio da Laconi, 11-13
09123 Cagliari (ITALIA)
Tel:  +39-0706753509
E-mail: elenasulis at hotmail.it<mailto:elenasulis at hotmail.it>
Skype: elena.sulis



_______________________________________________
IPMpack-users mailing list
IPMpack-users at lists.r-forge.r-project.org<mailto:IPMpack-users at lists.r-forge.r-project.org>
http://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/ipmpack-users


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/ipmpack-users/attachments/20160926/116bd72a/attachment.html>