This function organizes input and output for attributable risk analysis of categorical data generated by a probability survey.
attrisk.analysis(sites = NULL, subpop = NULL, design, data.ar,
response.var, stressor.var, response.levels = rep(list(c("Poor",
"Good")), length(response.var)), stressor.levels = rep(list(c("Poor",
"Good")), length(stressor.var)), popcorrect = FALSE, pcfsize = NULL,
N.cluster = NULL, stage1size = NULL, sizeweight = FALSE,
vartype = "Local", conf = 95)Data frame consisting of two variables: the first variable is site IDs, and the second variable is a logical vector indicating which sites to use in the analysis. The default is NULL.
Data frame describing sets of populations and subpopulations for which estimates will be calculated. The first variable is site IDs. Each subsequent variable identifies a Type of population, where the variable name is used to identify Type. A Type variable identifies each site with one of the subpopulations of that Type. The default is NULL.
Data frame consisting of design variables. Variables should be named as follows:
Vector of site IDs
Vector of weights, which are either the weights for a single-stage sample or the stage two weights for a two-stage sample
Vector of x-coordinates for location, which are either the x-coordinates for a single-stage sample or the stage two x-coordinates for a two-stage sample
Vector of y-coordinates for location, which are either the y-coordinates for a single-stage sample or the stage two y-coordinates for a two-stage sample
Vector of the stratum codes for each site
Vector of the stage one sampling unit (primary sampling unit or cluster) codes for each site
Vector of stage one weights in a two-stage design
Vector of the stage one x-coordinates for location in a two-stage design
Vector of the stage one y-coordinates for location in a two-stage design
Vector of support values - for a finite resource, the value one (1) for a for site. For an extensive resource, the measure of the sampling unit associated with a site. Required for calculation of finite and continuous population correction factors.
Vector of size-weights, which is the stage two size-weight for a two-stage design.
Vector of stage one size-weights for a two-stage design.
Data frame of categorical response and stressor variables, where each variable consists of two categories. If response or stressor variables include more than two categories, occurrences of those categories must be removed or replaced with missing values. The first column of this argument is site IDs. Subsequent columns are response and stressor variables. Missing data (NA) is allowed.
Character vector providing names of columns in argument data.ar that contain a response variable, where names may be repeated. Each name in this argument is matched with the corresponding value in the stressor.var argument.
Character vector providing names of columns in argument data.ar that contain a stressor variable, where names may be repeated. Each name in this argument is matched with the corresponding value in the response.var argument. This argument must be the same length as argument response.var.
List providing the category values (levels) for each element in the response.var argument. This argument must be the same length as argument response.var. The default is a list containing the values "Poor" and "Good" for the first and second levels, respectively, of each element in the response.var argument.
List providing the category values (levels) for each element in the stressor.var argument. This argument must be the same length as argument response.var. The default is a list containing the values "Poor" and "Good" for the first and second levels, respectively, of each element in the stressor.var argument.
Logical value that indicates whether finite or continuous population correction factors should be employed during variance estimation, where TRUE = use the correction factor and FALSE = do not use the correction factor. The default is FALSE. To employ the correction factor for a single-stage sample, values must be supplied for argument pcfsize and for the support variable of the design argument. To employ the correction factor for a two-stage sample, values must be supplied for arguments N.cluster and stage1size, and for the support variable of the design argument.
Size of the resource, which is required for calculation of finite and continuous population correction factors for a single-stage sample. For a stratified sample this argument must be a vector containing a value for each stratum and must have the names attribute set to identify the stratum codes. The default is NULL.
The number of stage one sampling units in the resource, which is required for calculation of finite and continuous population correction factors for a two-stage sample. For a stratified sample this argument must be a vector containing a value for each stratum and must have the names attribute set to identify the stratum codes. The default is NULL.
Size of the stage one sampling units of a two-stage sample, which is required for calculation of finite and continuous population correction factors for a two-stage sample and must have the names attribute set to identify the stage one sampling unit codes. For a stratified sample, the names attribute must be set to identify both stratum codes and stage one sampling unit codes using a convention where the two codes are separated by the & symbol, e.g., "Stratum 1&Cluster 1". The default is NULL.
Logical value that indicates whether size-weights should be used in the analysis, where TRUE = use the size-weights and FALSE = do not use the size-weights. The default is FALSE.
The choice of variance estimator, where "Local" = local mean estimator and "SRS" = SRS estimator. The default is "Local".
Numeric value for the confidence level. The default is 95.
A data frame of attributable risk estimates for all combinations of population Types, subpopulations within Types, and response variables. Standard error and confidence interval estimates also are provided.
Sarndal, C.E., B. Swensson, and J. Wretman. (1992). Model Assisted Survey Sampling. Springer-Verlag, New York.
attrisk.estcomputes the attributable risk estimate
dframe.checkcheck site IDs, the sites data frame, the subpop data frame, and the data.ar data frame to assure valid contents and, as necessary, create the sites data frame and the subpop data frame
uniqueIDcreates unique site IDs by appending a unique number to each occurrence of a site ID
input.checkcheck input values for errors, consistency, and compatibility with psurvey.analysis analytical functions
# NOT RUN {
mysiteID <- paste("Site", 1:100, sep="")
mysites <- data.frame(
siteID=mysiteID,
Active=rep(TRUE, 100))
mysubpop <- data.frame(
siteID=mysiteID,
All.Sites=rep("All Sites", 100),
Resource.Class=rep(c("Agr", "Forest"), c(55,45)))
mydesign <- data.frame(
siteID=mysiteID,
wgt=runif(100, 10, 100),
xcoord=runif(100),
ycoord=runif(100),
stratum=rep(c("Stratum1", "Stratum2"), 50))
mydata.ar <- data.frame(
siteID=mysiteID,
RespVar1=sample(c("Poor", "Good"), 100, replace=TRUE),
RespVar2=sample(c("Poor", "Good"), 100, replace=TRUE),
StressVar=sample(c("Poor", "Good"), 100, replace=TRUE))
attrisk.analysis(sites=mysites, subpop=mysubpop, design=mydesign,
data.ar=mydata.ar, response.var=c("RespVar1", "RespVar2"),
stressor.var=rep("StressVar", 2))
# }
Run the code above in your browser using DataLab