makeOffspringObj: Function to build offspring objects

In wpetry/IPMpack2: Builds and analyses Integral Projection Models (IPMs).

Function to build offspring objects

Description

A function that fits regressions that define offspring size and from these build growth objects for which methods to build an IPM object are defined; alternatively, the function creates offspring objects following a specified formula with specified coefficients and sd. Note that if an "offspringNext" column is available in the data, the data will be subsetted based on whether offspringType="sexual" or "clonal" (the default is "sexual"); - otherwise, appropriate data must be supplied.

Usage

makeOffspringObj(dataf=NULL, Formula = sizeNext ~ size, 
	regType = "constantVar", Family = "gaussian", link = NULL,
coeff=NULL,sd=NULL, reproductionType="sexual")

Arguments

dataf	a dataframe with columns ‘size’ and ‘sizeNext’(‘size’ is size of parent at t, and may not be known, ‘sizeNext’ is offspring size at t+1); facultatively, dataf may include ‘covariate’ and ‘covariatel’ for a single discrete covariate, indicating values at t, and at t+1, respectively; these must take values of sequential integers, starting at ‘1’.
Formula	a formula describing the desired explanatory variables (interactions, etc) according to the R notation for formula. style, i.e. separated by ‘+’, ‘*’, ‘:’ and response variable. Possible covariates include ‘size’, 'size2' (size^2), ‘size3’ (size^3),‘logsize’ (log(size)), ‘logsize2’ (log(size)^2), and ‘covariate’ (if this name is used, the assumption is made that this is a discrete covariate from which compound matrices may be constructed); or any other covariate available in dataf.
regType	possible values include ‘constantVar’ or ‘changingVar’
Family	possible values include ‘gaussian’, ‘poisson’, ‘negbin’
link	defaults to NULL, currently only relevant with Family="negbin", and only "log" and "identity" are permitted
coeff	numeric vector of required coefficients to be imposed if dataf is NULL; must be compatible with Formula
sd	numeric of required sd to be imposed if dataf is NULL
reproductionType	whether the relationship should be fitted for sexual or clonal offspring; the default is "sexual"; this will only be relevant if data is provided and has a column "offspringNext"

Value

An object of class growthObj, or growthObjPois, growthObjIncr, or growthObjLogIncr; or growthObjDeclineVar, or growthObjIncrDeclineVar, or growthObjLogIncrDeclineVar. These are S4 objects which contain the slots:

fit	an object of class lm or glm or gls that can be used with predict in the growth methods

Slots can be listed by using slotNames(growthObj)

Note

Note that DeclineVar objects cannot currently be constructed without a data-frame.

Author(s)

C. Jessica E. Metcalf, Sean M. McMahon, Roberto Salguero-Gomez & Eelke Jongejans

See Also

makeGrowthObj, makeSurvObj, makeFecObj

Examples

#generate data
dff <- generateData()

#make simple linear regression growth object relating size to size at t+1
off1 <- makeOffspringObj(dataf = dff, Formula = sizeNext~1)

#now specifying parameters and supplying no data
off1 <- makeOffspringObj(Formula = incr ~ size + covariate,coeff=c(1,1,1),sd=1)

##make an Fmatrix with this
dff<-generateData()
dff$fec[dff$fec==0] <- NA

off1 <- makeOffspringObj(dataf = dff, Formula = sizeNext~1)
fv1 <- makeFecObj(dff, Formula = fec~size, Transform = "log", 
    doOffspring=FALSE)
Fmatrix1 <- makeIPMFmatrix(fecObj = fv1, nBigMatrix = 20, 
	minSize = min(dff$size, na.rm = TRUE), maxSize = max(dff$size,
na.rm = TRUE), correction="constant", offspringObj=off1)

#compare with the other approach (where offspring object is not separate)
fv2 <- makeFecObj(dff, Formula = fec~size, Transform = "log",
	offspringSizeExplanatoryVariables = "1", doOffspring=TRUE)
Fmatrix2 <- makeIPMFmatrix(fecObj = fv2, nBigMatrix = 20, 
	minSize = min(dff$size, na.rm = TRUE), maxSize = max(dff$size,
na.rm = TRUE), correction="constant", offspringObj=NULL)

par(mfrow=c(1,2))
image(Fmatrix1); image(Fmatrix2)

wpetry/IPMpack2 documentation built on Sept. 29, 2022, 9:41 a.m.