ps_CV_corr: ps_CV_corr

In benmarwick/karon: Compositional Data Analysis of Archaeological Artefacts

ps_CV_corr

Description

Compute coefficients of variation and correlations for specified analytic values, by specified groups, and plots to visualize correlations. Observations with missing values are removed from computations using them.

Usage

ps_CV_corr(
  doc = "ps_CV_corr",
  data,
  GroupVar,
  Groups = "All",
  ByGroup = TRUE,
  ID = " ",
  AnalyticVars,
  Transpose = TRUE,
  CV_digits = 2,
  corr_digits = 2,
  plotCorrs = TRUE,
  folder = " "
)

Arguments

doc	A string with documentation, default is the function name
data	AR matrix or data frame containing the data to be analyzedfn
GroupVar	The name for the variable defining grouping; if " ", no grouping
Groups	Character valued defining the the groups used_ Options are a Vector of values of the group variable; "All" (the default; use all groups); " ", no grouping
ByGroup	If TRUE (the default), results are returned for each group in Groups; if FALSE, groups are combined
ID	The name of a variable with a lab ID (used for sorting data), default is " "
AnalyticVars	A vector of names (character values) of analytic results
Transpose	See Details
CV_digits	The number of significant digits in CV estimates, default is 2
corr_digits	The number of significant digits in correlation estimates, default is 2
plotCorrs	Logical, if TRUE (the default), create a matrix of plots describing correlations
folder	The path to the folder in which data frames will be saved; default is " "

Value

A list with the following components:

• usage: A vector with the contents of the argument doc, the date run, the version of R used

• dataUsed: The contents of the argument data restricted to the groups used

• dataNA: A data frame with observations containing a least one missing value for an analysis variable, NA if no missing values

• params: A list containing the values of the grouping,logical, and numeric parameters

• analyticVars: A vector with the value of the argument AnalyticVars

• CV: A data frame with the coefficients of variation for each analytic variable in each group

• corr: A data frame with the correlations between pairs of variables in each group

• location: The value of the parameter folder

Details

If Transpose=TRUE, the correlation matrix has rows defined by the group variable and columns defined by the pairs of analytic variables_ If Transpose=FALSE, the rows are defined by pairs of analytic variables and the columns are defined by the groups.

Examples

#  All sources combined
data(ObsidianSources)
analyticVars<-c("Rb","Sr","Y","Zr","Nb")
CV_corr<-ps_CV_corr(data = ObsidianSources, GroupVar="Code", Groups = "All",
 AnalyticVars=analyticVars, ByGroup=FALSE)

#  By source, restricted to two sources
data(ObsidianSources)
analyticVars<-c("Rb","Sr","Y","Zr","Nb")
CV_corr<-ps_CV_corr(data = ObsidianSources, GroupVar="Code", Groups = c("A","B"),
 AnalyticVars=analyticVars, ByGroup=TRUE)

benmarwick/karon documentation built on July 29, 2023, 10:11 a.m.