library(norm)
x <- read.table("cancer.dat", header = TRUE)
y <- as.matrix(x)  #convert table to matrix
summary(lm(formula = totbpt~Sexp +deptp+anxtp+depts+anxts, x))  #Use original data

###############

#  Data Augmentation using norm.R
s <- prelim.norm(y)  #get preliminary statistics for the analysis
thetahat <-em.norm(s)  #Get MLE for start value
rngseed(1234567)
theta <- da.norm(s, thetahat, steps=20, showits=TRUE) # GET MLE
getparam.norm(s, theta) #Print out those resulst
impdata <-imp.norm(s, theta, y)  #Impute the data
write(t(impdata), file = "impcancer", ncolumns = 9, sep = " ")
z <- data.frame(impdata)
summary(lm(formula = totbpt~Sexp +deptp+anxtp+depts+anxts,z))  #Use imputed data.

################

##  Imputing data using EM with single imputation
# Use results from first few steps above.
thetahat <- em.norm(s)  #Get MLE
getparam.norm(s, thetahat, corr = TRUE)  #look at est. correls
impdata <-imp.norm(s, theta, y)  #Impute the data
write(t(impdata), file = "impcancer", ncolumns = 9, sep = " ")
z <- data.frame(impdata)
summary(lm(formula = totbpt~Sexp +deptp+anxtp+depts+anxts,z))  #Use imputed data.


################

##  Imputing data using MULTIPLE Data Augmentation
#Same as first steps above
thetahat <- mda.norm(s, theta, steps = 5, showits = TRUE)  #Get MLE
getparam.norm(s, thetahat, corr = TRUE)  #look at est. correls
impdata <-imp.norm(s, theta, y)  #Impute the data
write(t(impdata), file = "impcancer", ncolumns = 9, sep = " ")
z <- data.frame(impdata)
summary(lm(formula = totbpt~Sexp +deptp+anxtp+depts+anxts,z))  #Use imputed data.