ma.wtd.statNA: Some Multivariate Descriptive Statistics for Weighted Data in miceadds

Description

Some multivariate descriptive statistics for weighted datasets in miceadds. A list of (nested) multiply imputed data sets is also allowed as input.

Usage

ma.wtd.meanNA(data, weights=NULL, vars=NULL )
ma.wtd.sdNA(data, weights=NULL, vars=NULL, method="unbiased" )
ma.wtd.covNA(data, weights=NULL, vars=NULL, method="unbiased" )
ma.wtd.corNA(data, weights=NULL, vars=NULL, method="unbiased" )
ma.wtd.skewnessNA(data, weights=NULL, vars=NULL, method="unbiased" )
ma.wtd.kurtosisNA(data, weights=NULL, vars=NULL, method="unbiased" )
ma.wtd.quantileNA( data, weights=NULL, vars=NULL, type=7,
          probs=seq(0,1,.25) )

Value

A vector or a matrix depending on the requested statistic.

Arguments

data: Numeric data vector or data frame or objects of one of the classes datlist, imputationList, mids, mids.1chain, nested.datlist, NestedImputationList or BIFIEdata.
weights: Optional vector of sampling weights
vars: Optional vector of variable names
method: Computation method for covariances. These amount to choosing the divisor \((n-1)\) (method="unbiased") instead of \(n\) (method="ML"). See stats::cov.wt for further details.
type: Quantile type. This specification follows TAM::weighted_quantile
probs: Vector of probabilities used for calculation of quantiles.

Details

Contrary to ordinary R practice, missing values are ignored in the calculation of descriptive statistics.

`ma.wtd.meanNA`	weighted means
`ma.wtd.sdNA`	weighted standard deviations
`ma.wtd.covNA`	weighted covariance matrix
`ma.wtd.corNA`	weighted correlation matrix
`ma.wtd.skewnessNA`	weighted skewness
`ma.wtd.kurtosisNA`	weighted (excess) kurtosis

Examples

Run this code

#############################################################################
# EXAMPLE 1: Weighted statistics for a single dataset data.ma01
#############################################################################

data(data.ma01)
dat <- as.matrix(data.ma01[,-c(1:3)])

# weighted mean
ma.wtd.meanNA( dat, weights=data.ma01$studwgt )

# weighted SD
ma.wtd.sdNA( dat, weights=data.ma01$studwgt )

# weighted covariance for selected variables
ma.wtd.covNA( dat, weights=data.ma01$studwgt, vars=c("books","hisei") )

# weighted correlation
ma.wtd.corNA( dat, weights=data.ma01$studwgt )

if (FALSE) {
# weighted skewness
ma.wtd.skewnessNA( dat[,"books"], weights=data.ma01$studwgt )
# compare with result in TAM
TAM::weighted_skewness( x=dat[,"books"], w=data.ma01$studwgt )

# weighted kurtosis
ma.wtd.kurtosisNA( dat, weights=data.ma01$studwgt, vars=c("books","hisei") )
# compare with TAM
TAM::weighted_kurtosis( dat[,"books"], w=data.ma01$studwgt )
TAM::weighted_kurtosis( dat[,"hisei"], w=data.ma01$studwgt )

#############################################################################
# EXAMPLE 2: Weighted statistics multiply imputed dataset
#############################################################################

library(mitools)
data(data.ma05)
dat <- data.ma05

# do imputations
resp <- dat[, - c(1:2) ]
# object of class mids
imp <- mice::mice( resp, method="norm", maxit=3, m=5 )
# object of class datlist
datlist <- miceadds::mids2datlist( imp )
# object of class imputationList
implist <- mitools::imputationList(datlist)

# weighted means
ma.wtd.meanNA(datlist)
ma.wtd.meanNA(implist)
ma.wtd.meanNA(imp)

# weighted quantiles
ma.wtd.quantileNA( implist, weights=data.ma05$studwgt, vars=c("manote","Dscore"))

#############################################################################
# EXAMPLE 3: Weighted statistics nested multiply imputed dataset
#############################################################################

library(BIFIEsurvey)
data(data.timss2, package="BIFIEsurvey" )
datlist <- data.timss2   # list of 5 datasets containing 5 plausible values

#** define imputation method and predictor matrix
data <- datlist[[1]]
V <- ncol(data)
# variables
vars <- colnames(data)
# variables not used for imputation
vars_unused <- miceadds::scan.vec("IDSTUD TOTWGT  JKZONE  JKREP" )
#- define imputation method
impMethod <- rep("norm", V )
names(impMethod) <- vars
impMethod[ vars_unused ] <- ""
#- define predictor matrix
predM <- matrix( 1, V, V )
colnames(predM) <- rownames(predM) <- vars
diag(predM) <- 0
predM[, vars_unused ] <- 0

# object of class mids.nmi
imp1 <- miceadds::mice.nmi( datlist, method=impMethod, predictorMatrix=predM,
                m=4, maxit=3 )
# object of class nested.datlist
datlist <- miceadds::mids2datlist(imp1)
# object of class NestedImputationList
imp2 <- miceadds::NestedImputationList(datlist)

# weighted correlations
vars <- c("books","ASMMAT","likesc")
ma.wtd.corNA( datlist,  vars=vars )
ma.wtd.corNA( imp2,  vars=vars )
ma.wtd.corNA( imp1,  vars=vars )

#############################################################################
# EXAMPLE 4: Multiply imputed datasets in BIFIEdata format
#############################################################################

library(BIFIEsurvey)
data(data.timss1, package="BIFIEsurvey")
data(data.timssrep, package="BIFIEsurvey")

# create BIFIEdata object
bdat <- BIFIEsurvey::BIFIE.data( data.list=data.timss1, wgt=data.timss1[[1]]$TOTWGT,
            wgtrep=data.timssrep[, -1 ] )
summary(bdat)
# create BIFIEdata object in a compact way
bdat2 <- BIFIEsurvey::BIFIE.data( data.list=data.timss1, wgt=data.timss1[[1]]$TOTWGT,
            wgtrep=data.timssrep[, -1 ], cdata=TRUE)
summary(bdat2)

# compute skewness
ma.wtd.skewnessNA( bdat, vars=c("ASMMAT", "books" ) )
ma.wtd.skewnessNA( bdat2, vars=c("ASMMAT", "books" ) )

#############################################################################
# EXAMPLE 5: Nested multiply imputed datasets in BIFIEdata format
#############################################################################

data(data.timss4, package="BIFIEsurvey")
data(data.timssrep, package="BIFIEsurvey")

# nested imputed dataset, save it in compact format
bdat <- BIFIE.data( data.list=data.timss4, wgt=data.timss4[[1]][[1]]$TOTWGT,
            wgtrep=data.timssrep[, -1 ], NMI=TRUE, cdata=TRUE )
summary(bdat)
# skewness
ma.wtd.skewnessNA( bdat, vars=c("ASMMAT", "books" ) )
}