sampleRealizations: Sample species patch realizations simulations

View source: R/sampleRealizations.R

sampleRealizationsR Documentation

Sample species patch realizations simulations

Description

This function simulates sampling of multiple realizations of patches of the species of interest within the grid of locations created with createPop. The number of total simulations is length(n1_vec) x length(popvar) x length(realvar)

Usage

sampleRealizations(
  popdata,
  sims,
  n1_vec,
  avar = NULL,
  ovar,
  rvar = NULL,
  SamplingDesign = "ACS",
  yvar,
  y_HT_formula = "y_HT",
  var_formula = "var_y_HT",
  m_threshold = NULL,
  f_max = 2,
  SampleEstimators = FALSE,
  SpatStat = TRUE,
  mChar = TRUE,
  popvar,
  realvar = "realization",
  weights = "S",
  seed = NA
)

Arguments

popdata

patch realizations

sims

Number of simulations per population.

n1_vec

Vector of initial sample size(s) for the initial simple random sample(s) without replacement; can be a single value or vector of values.

avar

The total vector of variables (c(avar, ovar, rvar)) should be a length of at least 1.

ovar

Vector of occupancy variables. The total vector of variables (c(avar, ovar, rvar)) should be a length of at least 1.

rvar

Vector of ratio variables. The total vector of variables (c(avar, ovar, rvar)) should be a length of at least 1.

SamplingDesign

A character string supplying the sampling design to use; accepted options included "SRS" (simple random sampling), "ACS" (unrestricted adaptive cluster sampling), and "RACS" (restricted ACS). The default is "ACS".

yvar

A string giving the name of the variable of interest, y, in the supplied dataframe popdata. This variable determines the condition under which adaptive cluster sampling takes place. In the dataframe $popdata$ this variable y must be numeric.

y_HT_formula

The formula used to estimate the population total: either the Horvitz-Thompson estimator, 'y_HT,' or or the RACS-corrected Horvitz-Thompson estimator, 'y_HT_RACS'.

var_formula

The formula used to estimate the variance of the population total: either the Horvitz-Thompson variance estimator, 'var_y_HT', or the RACS-corrected Horvitz-Thompson variance estimator, "var_y_HT_RACS." Defaults to "var_y_HT".

m_threshold

threshold value above which to calculate pi_i and pi_j differently.

f_max

The maximum number of expanding sets of adjacent units surveyed per primary unit in the adaptive phase of ACS. For more information, see Sauby and Christman (in prep).

SampleEstimators

If "TRUE", calculate the sample mean and sample variance for each simulation. Default is FALSE.

SpatStat

TRUE or FALSE. If "TRUE", for each simulation calculate Moran's I, and the nugget, sill, and range of the semivariogram. Default is TRUE.

mChar

TRUE or FALSE. If "TRUE", for each simulation calculate summary statistics (median, mean, min, and max) for the sample's m values. Also, for each simulation and for the set of unique m values, calculate the same summary statistics. If "FALSE," no summary statistics are calculated.

popvar

Categorical variable used to identify different populations.

realvar

Variable identifying each realization. Default is "realization"

weights

If SpatStat is "TRUE", this is a vector giving spatial weight matrix styles to use to calculate the Join Count and Moran's I statistics. Can take on values "W", "B", "C", "U", "S", and "minmax". See nb2listw for more details.

seed

A vector of numbers, equal in length to n1_vec, to set random seeds, if a goal is the ability to reproduce the random sampling.

References

\insertRef

saubyadaptiveACSampling

Examples

# sims=20
# n1_vec=c(5,10,20,40)
# population <- createPop(x_start = 1, x_end = 30, y_start = 1, y_end = 30)
# #' avar = NULL
# ovar = c(
# 	"Stricta",
# 	"Pusilla",
#  "Cactus",
#  "CACA_on_Pusilla",
# "CACA_on_Stricta",
# "MEPR_on_Pusilla",
# "MEPR_on_Stricta",
# "Old_Moth_Evidence_Pusilla",
# "Old_Moth_Evidence_Stricta"
# )
# data(CactusRealizations)
# popdata = CactusRealizations # WHY IS THERE ISLAND=NA
# simulation_data <- sampleRealizations(
# popdata = popdata,
# 	sims = sims,
# 	n1_vec = n1_vec,
# 	avar = avar,
# 	ovar = ovar,
# popvar="Island",
# yvar="Cactus"
# )
# sims=200
# n1_vec=c(75,150,225,300,350)
# simulation_data_SRSWOR <- sampleRealizations(
# popdata = popdata,
# sims = sims,
# n1_vec = n1_vec,
# avar = avar,
# ovar = ovar,
# popvar="Island"
# )

ksauby/ACS documentation built on Aug. 18, 2022, 3:33 a.m.