MISS {LaplacesDemon}  R Documentation 
Multiple Imputation Sequential Sampling
Description
This function performs multiple imputation (MI) on a numeric matrix by sequentially sampling variables with missing values, given all other variables in the data set.
Usage
MISS(X, Iterations=100, Algorithm="GS", Fit=NULL, verbose=TRUE)
Arguments
X 
This required argument accepts a numeric matrix of data that
contains both observed and missing values. Data set

Iterations 
This is the number of iterations to perform sequential sampling via MCMC algorithms. 
Algorithm 
The MCMC algorithm defaults to the Gibbs Sampler (GS). 
Fit 
This optional argument accepts an object of class

verbose 
Logical. When 
Details
Imputation is a family of statistical methods for replacing missing values with estimates. Introduced by Rubin and Schenker (1986) and Rubin (1987), Multiple Imputation (MI) is a family of imputation methods that includes multiple estimates, and therefore includes variability of the estimates.
The Multiple Imputation Sequential Sampler (MISS) function performs MI by determining the type of variable and therefore the sampler for each variable, and then sequentially progresses through each variable in the data set that has missing values, updating its prediction of those missing values given all other variables in the data set each iteration.
MI is best performed within a model, where it is called
fulllikelihood imputation. Examples may be found in the "Examples"
vignette. However, sometimes it is impractical to impute within a
model when there are numerous missing values and a large number of
parameters are therefore added. As an alternative, MI may be
performed on the data set before the data is passed to the model,
such as in the IterativeQuadrature
,
LaplaceApproximation
, LaplacesDemon
, or
VariationalBayes
function. This is less desirable, but
MISS is available for MCMCbased MI in this case.
Missing values are initially set to column means for continuous variables, and are set to one for discrete variables.
MISS uses the following methods and MCMC algorithms:
Missing values of continuous variables are estimated with a ridgestabilized linear regression Gibbs sampler.
Missing values of binary variables that have only 0 or 1 for values are estimated either with a binary robit (tlink logistic regression model) Gibbs sampler of Albert and Chib (1993).
Missing values of discrete variables with 3 or more (ordered or unordered) discrete values are considered continuous.
In the presence of big data, it is suggested that the user sequentially read in batches of data that are small enough to be manageable, and then apply the MISS function to each batch. Each batch should be representative of the whole, of course.
It is common for multiple imputation functions to handle variable transformations. MISS does not transform variables, but imputes what it gets. For example, if a user has a variable that should be positive only, then it is recommended here that the user logtransform the variable, pass the data set to MISS, and when finished, exponentiate both the observed and imputed values of that variable.
The CenterScale
function should also be considered to speed up
convergence.
It is hoped that MISS is helpful, though it is not without limitation
and there are numerous alternatives outside of the
LaplacesDemon
package. If MISS does not fulfill the needs of
the user, then the following packages are recommended: Amelia, mi, or
mice. MISS emphasizes MCMC more than these alternatives, though MISS is
not as extensive. When a data set does not have a simple structure,
such as merely continuous or binary or unordered discrete, the
LaplacesDemon
function should be considered, where a
user can easily specify complicated structures such as multilevel,
spatial or temporal dependence, and more.
Matrix inversions are required in the Gibbs sampler. Matrix inversions
become more cumbersome as the number J
of variables increases.
If a large number of iterations is used, then the user may consider
studying the imputations for approximate convergence with the
BMK.Diagnostic
function, by supplying the transpose of
codeFit$Imp. In the presence of numerous missing values, say more
than 100, the user may consider iterating through the study of the
imputations of 100 missing values at a time.
Value
This function returns an object of class miss
that is a list
with five components:
Algorithm 
This indicates which algorithm was selected. 
Imp 
This is a 
parm 
This is a list of length 
PostMode 
This is a vector of posterior modes. If the user intends to replace missing values in a data set with only one estimate per missing values (single, not multiple imputation), then this vector contains these values. 
Type 
This is a vector of length 
Author(s)
Statisticat, LLC software@bayesianinference.com
References
Albert, J.H. and Chib, S. (1993). "Bayesian Analysis of Binary and Polychotomous Response Data". Journal of the American Statistical Association, 88(422), p. 669–679.
Rubin, D.B. (1987). "Multiple Imputation for Nonresponse in Surveys". John Wiley and Sons: New York, NY.
Rubin, D.B. and Schenker, N. (1986). "Multiple Imputation for Interval Estimation from Simple Random Samples with Ignorable Nonresponse". Journal of the American Statistical Association, 81, p. 366–374.
See Also
ABB
,
BMK.Diagnostic
,
CenterScale
,
IterativeQuadrature
LaplaceApproximation
,
LaplacesDemon
, and
VariationalBayes
.
Examples
#library(LaplacesDemon)
### Create Data
#N < 20 #Number of Simulated Records
#J < 5 #Number of Simulated Variables
#pM < 0.25 #Percent Missing
#Sigma < as.positive.definite(matrix(runif(J*J),J,J))
#X < rmvn(N, rep(0,J), Sigma)
#m < sample.int(N*J, round(pM*N*J))
#X[m] < NA
#head(X)
### Begin Multiple Imputation
#Fit < MISS(X, Iterations=100, Algorithm="GS", verbose=TRUE)
#Fit
#summary(Fit)
#plot(Fit)
#plot(BMK.Diagnostic(t(Fit$Imp)))
### Continue Updating if Necessary
#Fit < MISS(X, Iterations=100, Algorithm="GS", Fit, verbose=TRUE)
#summary(Fit)
#plot(Fit)
#plot(BMK.Diagnostic(t(Fit$Imp)))
### Replace Missing Values in Data Set with Posterior Modes
#Ximp < X
#Ximp[which(is.na(X))] < Fit$PostMode
### Original and Imputed Data Sets
#head(X)
#head(Ximp)
#summary(X)
#summary(Ximp)
### or Multiple Data Sets, say 3
#Ximp < array(X, dim=c(nrow(X), ncol(X), 3))
#for (i in 1:3) {
# Xi < X
# Xi[which(is.na(X))] < Fit$Imp[,sample.int(ncol(Fit$Imp), 1)]
# Ximp[,,i] < Xi}
#head(X)
#head(Ximp[,,1])
#head(Ximp[,,2])
#head(Ximp[,,3])
#End