ImputeRegressionMulti: Imputation of a several variables (y's) by a regression model...

In statisticsnorway/Kostra: Functions for Kostra

Imputation of a several variables (y's) by a regression model using a single explanatory variable (x).

Description

Impute missing and wrong values (group 3) by the model based on representative data (group 1). Some data are considered correct but not representative (group 2). This grouping is common for all y-variables.

Usage

ImputeRegressionMulti(
  data,
  idName = names(data)[1],
  strataName = NULL,
  xName = names(data)[3],
  yNames = names(data)[4:NCOL(data)],
  ySelect = 1:length(yNames),
  methodOneComp = "mean",
  method = "ordinary",
  limitModel = 2.5,
  limitIterate = 4.5,
  limitImpute = 50,
  returnSameType = TRUE
)

ImputeRegressionMultiNewNames(...)

ImputeRegressionMultiTall(..., iD = TalliD())

ImputeRegressionMultiTallSmall(..., iD = TalliD(), keep = c("ID", "nImputed"))

ImputeRegressionMultiWide(
  ...,
  addName = WideAddName(),
  sep = WideSep(),
  idNames = c("", "strata", ""),
  addLast = FALSE
)

ImputeRegressionMultiWideSmall(
  ...,
  keep = c("id", "strata", "nImputed"),
  addName = WideAddName(),
  sep = WideSep(),
  idNames = c("", "strata", ""),
  addLast = FALSE
)

Arguments

data	Input data set of class data.frame
idName	Name of id-variable(s)
strataName	Name of starta-variable. Single strata when NULL (default)
xName	Name of x-variable
yNames	Names of y-variables
ySelect	Indices of yNames to extract a single component from
methodOneComp	Method used to extract a single component coded as a string: "mean" (default),"pca","pcaMedian" or "pcaStd"
method	The method (model and weight) coded as a string: "ordinary" (default), "ratio", "noconstant", "mean" or "ratioconstant".
limitModel	Studentized residuals limit. Above limit -> group 2.
limitIterate	Studentized residuals limit for iterative calculation of studentized residuals.
limitImpute	Studentized residuals limit. Above limit -> group 3.
returnSameType	When TRUE (default) and when the type of input y variables is integer, the output type of imputations and estimates from the final run is also integer. Those estimates/sums are then calculated from rounded imputed values.

Details

Multivariate imputations are performed by running an imputation model within each strata. Thus, the three groups (category123) are the same for all y-variables. Division into the three groups are based on studentized residuals from a inititial run with a single variable. Calculations of studentized residuals are performed by iterativily throwing out observations from the model fitting. The single initial variable can be a original variable (ySelect is a single number) or a component extracted according to methodOneComp.

Calculations of studentized residuals are performed by iterativily throwing out observations from the model fitting.

Missing x-values are not allowed in this version.

Value

Output of the alternative variants of the function (Tall, Wide, Small) are constructed similar to the variants of ImputeRegression.

Output of ImputeRegressionMulti and ImputeRegressionMultiNewNames (using the names after or below) is a list where the first three elements are ouput from the initial run with a single variable: micro has as many rows as input, aggregates has one row for each strata and total has a single row. The individual variables of these three elements are:

micro consists of the following elements:

id	id from input
x	The input x variable
y	The input y variable
strata	The input strata variable (can be NULL)
category123	The three imputation groups: representative (1), correct but not representative (2), wrong (3).
yHat \emph{or estimateYHat}	Fitted values
yImputed \emph{or estimate}	Imputed y-data
rStud	The final studentized residuals
dffits	The final DFFITS statistic
hii	The final leverages (diagonal elements of hat matrix)
leaveOutResid	The final outside-model residual

aggregates consists of the following elements:

N	Number of observations in each strata
nImputed	Number of imputed observations in each strata
estimate	Total estimates from imputed data
cv	Coefficient of variation = seEstimate/estimate
estimateYhat	Totale estimate based on model fits
estimateOrig \emph{or y}	Estimate based on original data with missing set to zero
coef	The final first model coefficient
coefB	The final second model coefficient or zeros when only one coefficient in model.
n	The final number of observations in model.
sigmaHat	The final square root of the estimated variance parameter
seEstimate	The final standard error estimate of the total estimate from imputed data
seRobust	Robust variant of seEstimate (experimental)

total consists of the following elements:

Ntotal \emph{or N}	Number of observations
nImputedTotal \emph{or nImputed}	Total number of imputed observations
estimateTotal \emph{or estimate}	Total estimate for all strata
cvTotal or \emph{cv}	Total cv for all strata

The other output elements are from the final run with all y-variables. These elements are:

\strong{MyImputed}	Matrix of imputed y-data
\strong{Mestimate}	Matrix of total estimates from imputed data
\strong{Mcv}	Matrix of coefficient of variation = seEstimate/estimate
\strong{MestimateTotal}	Matrix of total estimates for all strata (a single row)
\strong{McvTotal}	Matrix of total cvs for all strata (a single row)

Examples

z=KostraData("ratioTest")
z2=cbind(id=10*(1:NROW(z)),z[,c(3,1,2)],y2=z$y+z$x)
ImputeRegressionMulti(z2,strataName="k",method="ratio")
ImputeRegressionMultiNewNames(z2,strataName="k")
ImputeRegressionMultiTall(z2,strataName="k")
ImputeRegressionMultiTallSmall(z2,strataName="k")
ImputeRegressionMultiWide(z2,strataName="k")
ImputeRegressionMultiWideSmall(z2,strataName="k")

rateData <- KostraData("rateData")               # Real Kostra data set
w <- rateData$data[, c(17,19,16,5:10)]           # Data with id, strata, x and many ys
w <- w[is.finite(w[,"Ny.kostragruppe"]), ]       # Remove Longyearbyen
w[w[,"Ny.kostragruppe"]>13,"Ny.kostragruppe"]=13 # Combine small strata
ImputeRegressionMulti(w, strataName = names(w)[2])
names(w)[4:9] = paste("y",1:6,sep="")           # rename for nicer output
ImputeRegressionMulti(w, strataName = names(w)[2], method="ratio")
ImputeRegressionMulti(w, method="ratioconstant") # No strata

statisticsnorway/Kostra documentation built on Nov. 2, 2024, 6:40 p.m.