mi.count: Elementary function: Bayesian overdispersed poisson regression to impute a count variable.
Description
Imputes univariate missing data using bayesglm, an
R functions for generalized linear modeling with independent normal, t, or
Cauchy prior distribution for the coefficients.
Usage
mi.count(formula, data = NULL, start = NULL, maxit = 100,
draw.from.beta = TRUE, missing.index = NULL, ...)
## S3 method for class 'mi.count':
resid(object, y)
## S3 method for class 'mi.count':
residuals(object, y)
Arguments
formula
an object of class formula (or one that can be coerced to that class):
a symbolic description of the model to be fitted. See bayesglm formula for details.
data
A data frame containing the incomplete data and the matrix of the complete predictors.
start
Starting value for bayesglm.
maxit
Maximum number of iteration for bayesglm. The default is 100.
draw.from.beta
Draws from posterior distribution of the betas to add randomness.
missing.index
The index of missing units of the outcome variable
...
Currently not used.
object
mi.countr object.
y
Observed values.
Value
modelA summary of the bayesian fitted model.
expectedThe expected values estimated by the model.
randomVector of length n.mis of random predicted values predicted by using the binomial distribution.
Details
In bayesglm default the prior distribution is Cauchy with center 0 and scale 2.5
for all coefficients (except for the intercept, which has a prior scale of 10).
See also glm for other details.
References
Yu-Sung Su, Andrew Gelman, Jennifer Hill, Masanao Yajima. (2011).
Multiple Imputation with Diagnostics (mi) in R: Opening Windows into the Black Box.
Journal of Statistical Software 45(2).
Andrew Gelman and Jennifer Hill,
Data Analysis Using Regression and Multilevel/Hierarchical Models,
Cambridge University Press, 2007.
# true data x <- rnorm(100,0,1)
y <- rpois(100,40)
# create artificial missingness on y y [seq(1,100,10)] <- NA dat.xy <- data.frame(x,y)
# imputation mi.count(y ~ x, data = dat.xy)