PVAClone-package: Population Viability Analysis with Data Cloning

Description Details Author(s) References See Also Examples

Description

Likelihood based population viability analysis in the presence of observation error and missing data. The package can be used to fit, compare, predict, and forecast various growth model types using data cloning.

Details

The package implements data cloning based population viability analysis methodology developed by Nadeem and Lele (2012). This includes model estimation, model selection and forecasting of future population abundances for estimate the extinction risk of a population of interest.

pva: main function for model fitting.

model.select: main function for model model selection.

Growth models: gompertz, ricker, bevertonholt, thetalogistic, thetalogistic_D.

Author(s)

Khurram Nadeem, Peter Solymos

Maintainer: Peter Solymos <solymos@ualberta.ca>

References

Nadeem, K., Lele S. R., 2012. Likelihood based population viability analysis in the presence of observation error. Oikos 121, 1656–1664.

See Also

pva

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
## Not run: 
## model selection for data with missing observations
data(songsparrow)
## model without observation error
m1 <- pva(songsparrow, gompertz("none"), 2, n.iter=1000)
## model with Poisson observation error
m2 <- pva(songsparrow, gompertz("poisson"), 2, n.iter=1000)
## model with Poisson observation error is strongly supported
model.select(m1, m2)

## End(Not run)

Example output

Loading required package: dcmle
Loading required package: dclone
Loading required package: coda
Loading required package: parallel
Loading required package: Matrix
dclone 2.1-2 	 2016-03-11
dcmle 0.3-1 	 2016-03-11

Attaching package: 'dcmle'

The following objects are masked from 'package:coda':

    chanames, crosscorr.plot, gelman.diag, gelman.plot, geweke.diag,
    heidel.diag, raftery.diag, varnames

Loading required package: stats4
PVAClone 0.1-6 	 2016-03-11 
    check out ?PVA for an overview
Compiling model graph
   Resolving undeclared variables
   Allocating nodes
Graph information:
   Observed stochastic nodes: 48
   Unobserved stochastic nodes: 3
   Total graph size: 268

Initializing model

Compiling model graph
   Resolving undeclared variables
   Allocating nodes
Graph information:
   Observed stochastic nodes: 48
   Unobserved stochastic nodes: 51
   Total graph size: 654

Initializing model

Compiling model graph
   Resolving undeclared variables
   Allocating nodes
Graph information:
   Observed stochastic nodes: 24
   Unobserved stochastic nodes: 24
   Total graph size: 341

Initializing model

PVA Model Selection:
Time series with 24 observations (missing: 0) 

Null Model: m1 
   Gompertz growth model without observation error 

Alternative Model: m2 
   Gompertz growth model with Poisson observation error 

     log_LR delta_AIC delta_BIC delta_AICc
1 -90.73085  181.4617  181.4617   181.4617

Alternative Model is strongly supported over the Null Model

PVAClone documentation built on May 2, 2019, 5:49 a.m.