historicalize3() returns a vertically formatted demographic data frame
organized to create historical projection matrices, given a vertically but
ahistorically formatted data frame. This data frame is in standard
lefko3 format and can be used in all functions in the package.
historicalize3(
data,
popidcol = 0,
patchidcol = 0,
individcol,
year2col = 0,
year3col = 0,
xcol = 0,
ycol = 0,
sizea2col = 0,
sizea3col = 0,
sizeb2col = 0,
sizeb3col = 0,
sizec2col = 0,
sizec3col = 0,
repstra2col = 0,
repstra3col = 0,
repstrb2col = 0,
repstrb3col = 0,
feca2col = 0,
feca3col = 0,
fecb2col = 0,
fecb3col = 0,
indcova2col = 0,
indcova3col = 0,
indcovb2col = 0,
indcovb3col = 0,
indcovc2col = 0,
indcovc3col = 0,
alive2col = 0,
alive3col = 0,
dead2col = 0,
dead3col = 0,
obs2col = 0,
obs3col = 0,
nonobs2col = 0,
nonobs3col = 0,
repstrrel = 1,
fecrel = 1,
stage2col = 0,
stage3col = 0,
juv2col = 0,
juv3col = 0,
stageassign = NA,
stagesize = NA,
censor = FALSE,
censorcol = 0,
censorkeep = 0,
spacing = NA,
NAas0 = FALSE,
NRasRep = FALSE,
reduce = TRUE
)The horizontal data file.
A variable name or column number corresponding to the identity of the population for each individual.
A variable name or column number corresponding to the identity of the patch for each individual, if patches have been designated within populations.
A variable name or column number corresponding to the unique identity of each individual.
A variable name or column number corresponding to occasion t (year or time).
A variable name or column number corresponding to occasion t+1 (year or time).
A variable name or column number corresponding to the x coordinate of each individual in Cartesian space.
A variable name or column number corresponding to the y coordinate of each individual in Cartesian space.
A variable name or column number corresponding to the primary size entry in occasion t.
A variable name or column number corresponding to the primary size entry in occasion t+1.
A variable name or column number corresponding to the secondary size entry in occasion t.
A variable name or column number corresponding to the secondary size entry in occasion t+1.
A variable name or column number corresponding to the tertiary size entry in occasion t.
A variable name or column number corresponding to the tertiary size entry in occasion t+1.
A variable name or column number corresponding to the production of reproductive structures, such as flowers, in occasion t. This can be binomial or count data, and is used to in analysis of the probability of reproduction.
A variable name or column number corresponding to the production of reproductive structures, such as flowers, in occasion t+1. This can be binomial or count data, and is used to in analysis of the probability of reproduction.
A second variable name or column number corresponding to the production of reproductive structures, such as flowers, in occasion t. This can be binomial or count data.
A second variable name or column number corresponding to the production of reproductive structures, such as flowers, in occasion t+1. This can be binomial or count data.
A variable name or column number corresponding to fecundity in occasion t. This may represent egg counts, fruit counts, seed production, etc.
A variable name or column number corresponding to fecundity in occasion t+1. This may represent egg counts, fruit counts, seed production, etc.
A second variable name or column number corresponding to fecundity in occasion t. This may represent egg counts, fruit counts, seed production, etc.
A second variable name or column number corresponding to fecundity in occasion t+1. This may represent egg counts, fruit counts, seed production, etc.
A variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t.
A variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t+1.
A second variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t.
A second variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t+1.
A third variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t.
A third variable name or column number corresponding to an individual covariate to be used in analysis, in occasion t+1.
A variable name or column number that provides information on whether an individual is alive in occasion t. If used, living status must be designated as binomial (living = 1, dead = 0).
A variable name or column number that provides information on whether an individual is alive in occasion t+1. If used, living status must be designated as binomial (living = 1, dead = 0).
A variable name or column number that provides information on whether an individual is dead in occasion t. If used, dead status must be designated as binomial (dead = 1, living = 0).
A variable name or column number that provides information on whether an individual is dead in occasion t+1. If used, dead status must be designated as binomial (dead = 1, living = 0).
A variable name or column number providing information on whether an individual is in an observable stage in occasion t. If used, observation status must be designated as binomial (observed = 1, not observed = 0).
A variable name or column number providing information on whether an individual is in an observable stage in occasion t+1. If used, observation status must be designated as binomial (observed = 1, not observed = 0).
A variable name or column number providing information on whether an individual is in an unobservable stage in occasion t. If used, observation status must be designated as binomial (not observed = 1, observed = 0).
A variable name or column number providing information on whether an individual is in an unobservable stage in occasion t+1. If used, observation status must be designated as binomial (not observed = 1, observed = 0).
This is a scalar multiplier to make the variable represented
by repstrb2col equivalent to the variable represented by
repstra2col. This can be useful if two reproductive status variables
have related but unequal units, for example if repstrb2col refers to
one-flowered stems while repstra2col refers to two-flowered stems.
This is a scalar multiplier that makes the variable represented
by fecb2col equivalent to the variable represented by feca2col.
This can be useful if two fecundity variables have related but unequal units.
Optional variable name or column number corresponding to life history stage in occasion t.
Optional variable name or column number corresponding to life history stage in occasion t+1.
A variable name or column number that marks individuals in
immature stages in occasion t. The historicalize3() function
assumes that immature individuals are identified in this variable marked with
a number equal to or greater than 1, and that mature individuals are marked
as 0 or NA.
A variable name or column number that marks individuals in
immature stages in occasion t+1. The historicalize3() function
assumes that immature individuals are identified in this variable marked with
a number equal to or greater than 1, and that mature individuals are marked
as 0 or NA.
The stageframe object identifying the life history model
being operationalized. Note that if stage2col is provided, then this
stageframe is not utilized in stage designation.
A variable name or column number describing which size
variable to use in stage estimation. Defaults to NA, and can also take
sizea, sizeb, sizec, or sizeadded, depending on
which size variable is chosen.
A logical variable determining whether the output data should
be censored using the variable defined in censorcol. Defaults to
FALSE.
A variable name or column number corresponding to a censor variable within the dataset, used to distinguish between entries to use and those to discard from analysis, or to designate entries with special issues that require further attention.
The value of the censoring variable identifying data that should be included in analysis. Defaults to 0, but may take any value including NA.
The spacing at which density should be estimated, if density
estimation is desired and x and y coordinates are supplied. Given in the same
units as those used in the x and y coordinates given in xcol and
ycol. Defaults to NA.
If TRUE, then all NA entries for size and fecundity variables
will be set to 0. This can help increase the sample size analyzed by
modelsearch(), but should only be used when it is clear that
this substitution is biologically realistic. Defaults to FALSE.
If set to TRUE, then this function will treat non-reproductive
but mature individuals as reproductive during stage zssignment. This can be
useful when a matrix is desired without separation of reproductive and
non-reproductive but mature stages of the same size. Only used if
stageassign is set to a stageframe. Defaults to FALSE.
A logical variable determining whether unused variables and some invariant state variables should be removed from the output dataset. Defaults to TRUE.
If all inputs are properly formatted, then this function will output
a historical vertical data frame (class hfvdata), meaning that the
output data frame will have three consecutive years of size and reproductive
data per individual per row. This data frame is in standard format for all
functions used in lefko3, and so can be used without further
modification. Note that determination of state in occasions *t*-1 and *t*+1
gives preference to condition in occasion *t* within the input dataset.
Conflicts in condition in input datasets that have both occasions *t* and
*t*+1 listed per row are resolved by using condition in occasion *t*.
Variables in this data frame include the following:
Unique identifier for the row of the data frame.
Unique identifier for the population, if given.
Unique identifier for patch within population, if given.
Unique identifier for the individual.
Year or time in occasion t.
Occasion of first observation.
Occasion of last observation.
Observed age in occasion t, assuming first observation corresponds to age = 0.
Observed lifespan, given as lastseen - firstseen + 1.
X position in Cartesian space in occasions t-1, t, and t+1, respectively, if provided.
Y position in Cartesian space in occasions t-1, t, and t+1, respectively, if provided.
Main size measurement in occasions t-1, t, and t+1, respectively.
Secondary size measurement in occasions t-1, t, and t+1, respectively.
Tertiary measurement in occasions t-1, t, and t+1, respectively.
Sum of primary, secondary, and tertiary size measurements in occasions t-1, t, and t+1, respectively.
Main numbers of reproductive structures in occasions t-1, t, and t+1, respectively.
Secondary numbers of reproductive structures in occasions t-1, t, and t+1, respectively.
Sum of primary and secondary reproductive structures in occasions t-1, t, and t+1, respectively.
Main numbers of offspring in occasions t-1, t, and t+1, respectively.
Secondary numbers of offspring in occasions t-1, t, and t+1, respectively.
Sum of primary and secondary fecundity in occasions t-1, t, and t+1, respectively.
Censor state values in occasions t-1, t, and t+1, respectively.
Binomial variable indicating whether
individual is juvenile in occasions t-1, t, and t+1.
Only given if juvcol is provided.
Binomial observation state in occasions t-1, t, and t+1, respectively.
Binomial reproductive state in occasions t-1, t, and t+1, respectively.
Binomial offspring production state in occasions t-1, t, and t+1, respectively.
Binomial maturity state in occasions t-1, t, and t+1, respectively.
Binomial state as alive in occasions t-1, t, and t+1, respectively.
Density of individuals per unit designated in spacing.
Only given if spacing is not NA.
In some datasets on species with unobserveable stages, observation status
(obsstatus) might not be inferred properly if a single size variable
is used that does not yield sizes greater than 0 in all cases in which
individuals were observed. Such situations may arise, for example, in plants
when leaf number is the dominant size variable used, but individuals
occasionally occur with inflorescences but no leaves. In this instances,
it helps to mark related variables as sizeb and sizec, because
observation status will be interpreted in relation to all 3 size variables.
Further analysis can then utilize only a single size variable, of the user's
choosing. Similar issues can arise in reproductive status (repstatus).
Warnings that some individuals occur in state combinations that do not match
any stages in the stageframe used to assign stages are common when first
working with a dataset. Typically, these situations can be identified as
NoMatch entries in stage3, although such entries may crop up in
stage1 and stage2, as well. In rare cases, these warnings will
arise with no concurrent NoMatch entries, which indicates that the
input dataset contained conflicting state data at once suggesting that the
individual is in some stage but is also dead. The latter is removed if the
conflict occurs in occasion t or occasion t-1, as only living
entries are allowed in these times.
Care should be taken to avoid variables with negative values indicating size, fecundity, or reproductive or observation status. Negative values can be interpreted in different ways, typically reflecting estimation through other algorithms rather than actual measured data. Variables holding negative values can conflict with data management algorithms in ways that are difficult to predict.
# NOT RUN {
data(cypvert)
sizevector <- c(0, 0, 0, 0, 0, 0, 1, 2.5, 4.5, 8, 17.5)
stagevector <- c("SD", "P1", "P2", "P3", "SL", "D", "XSm", "Sm", "Md", "Lg",
"XLg")
repvector <- c(0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1)
obsvector <- c(0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1)
matvector <- c(0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1)
immvector <- c(0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0)
propvector <- c(1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
indataset <- c(0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1)
binvec <- c(0, 0, 0, 0, 0, 0.5, 0.5, 1, 1, 2.5, 7)
cypframe_raw <- sf_create(sizes = sizevector, stagenames = stagevector,
repstatus = repvector, obsstatus = obsvector, matstatus = matvector,
propstatus = propvector, immstatus = immvector, indataset = indataset,
binhalfwidth = binvec)
cypframe_raw
cypraw_v2 <- historicalize3(data = cypvert, patchidcol = "patch",
individcol = "plantid", year2col = "year2", sizea2col = "Inf2.2",
sizea3col = "Inf2.3", sizeb2col = "Inf.2", sizeb3col = "Inf.3",
sizec2col = "Veg.2", sizec3col = "Veg.3", repstra2col = "Inf2.2",
repstra3col = "Inf2.3", repstrb2col = "Inf.2", repstrb3col = "Inf.3",
feca2col = "Pod.2", feca3col = "Pod.3", repstrrel = 2,
stageassign = cypframe_raw, stagesize = "sizeadded", censorcol = "censor",
censor = FALSE, NAas0 = TRUE, NRasRep = TRUE, reduce = TRUE)
cypsupp2r <- supplemental(stage3 = c("SD", "P1", "P2", "P3", "SL", "D",
"XSm", "Sm", "SD", "P1"),
stage2 = c("SD", "SD", "P1", "P2", "P3", "SL", "SL", "SL", "rep",
"rep"),
eststage3 = c(NA, NA, NA, NA, NA, "D", "XSm", "Sm", NA, NA),
eststage2 = c(NA, NA, NA, NA, NA, "XSm", "XSm", "XSm", NA, NA),
givenrate = c(0.10, 0.20, 0.20, 0.20, 0.25, NA, NA, NA, NA, NA),
multiplier = c(NA, NA, NA, NA, NA, NA, NA, NA, 0.5, 0.5),
type =c(1, 1, 1, 1, 1, 1, 1, 1, 3, 3),
stageframe = cypframe_raw, historical = FALSE)
cypmatrix2r <- rlefko2(data = cypraw_v2, stageframe = cypframe_raw,
year = "all", patch = "all", stages = c("stage3", "stage2"),
size = c("size3added", "size2added"), supplement = cypsupp2r,
yearcol = "year2", patchcol = "patchid", indivcol = "individ")
cypmatrix2r$A[[intersect(which(cypmatrix2r$labels$patch == "A"),
which(cypmatrix2r$labels$year2 == 2004))]]
lambda3(cypmatrix2r)
# }
Run the code above in your browser using DataLab