JointAI (version 0.1.0)

model_imp: Joint analysis and imputation of incomplete data

Description

lm_imp, glm_imp and lme_imp estimate linear, generalized linear and linear mixed models, respectively, using MCMC sampling.

Usage

lm_imp(formula, data, n.chains = 3, n.adapt = 100, n.iter = 0, thin = 1,
  monitor_params = NULL, inits = TRUE, modelname = NULL,
  modeldir = NULL, overwrite = FALSE, keep_model = FALSE, quiet = TRUE,
  progress.bar = "text", warn = TRUE, auxvars = NULL, meth = NULL,
  refcats = NULL, scale_vars = NULL, hyperpars = NULL, ...)
glm_imp(formula, family, data, n.chains = 3, n.adapt = 100, n.iter = 0,
  thin = 1, monitor_params = NULL, inits = TRUE, modelname = NULL,
  modeldir = NULL, overwrite = FALSE, keep_model = FALSE, quiet = TRUE,
  progress.bar = "text", warn = TRUE, auxvars = NULL, meth = NULL,
  refcats = NULL, scale_vars = NULL, hyperpars = NULL, ...)
lme_imp(fixed, data, random, n.chains = 3, n.adapt = 100, n.iter = 0,
  thin = 1, monitor_params = NULL, inits = TRUE, modelname = NULL,
  modeldir = NULL, overwrite = FALSE, keep_model = FALSE, quiet = TRUE,
  progress.bar = "text", warn = TRUE, auxvars = NULL, meth = NULL,
  refcats = NULL, scale_vars = NULL, hyperpars = NULL, ...)

Value

An object of class JointAI

Optional arguments

There are some optional parameters that can be passed to …

scale_pars

optional matrix of parameters used for centering and scaling continuous covariates. If not specified, this will be calculated automatically. If FALSE, no scaling will be done.

Details

Implemented distribution families and link functions for glm_imp()

gaussian	with links: identity, log
binomial	with links: logit, probit, log, cloglog
Gamma	with links: identity, log
poisson	with links: log, identity

Imputation methods

Implemented imputation models that can be chosen in the argument meth are:

norm	linear model
lognorm	log-linear model for skewed continuous data
logit	logistic model for binary data
multinomial	multinomial logit model for unordered categorical variables
ordinal	cumulative logit model for ordered categorical variables

Parameters to follow (monitor_params)

Named vector specifying which parameters should be monitored. This can be done either directly by specifying the name of the parameter or indirectly by one of the key words summarizing a number of parameters. Except for other, in which parameter names are specified directly, parameter (groups) are just set as TRUE or FALSE. If left unspecified, monitor_params = c("analysis_main" = TRUE) will be used.

name/key word	what is monitored
analysis_main	betas, tau_y and sigma_y
analysis_random	ranef, D, invD, RinvD
imp_pars	alphas, tau_imp, gamma_imp, delta_imp
imps	imputed values
betas	regression coefficients of the analysis model
tau_y	precision of the residuals from the analysis model
sigma_y	standard deviation of the residuals from the analysis model
ranef	random effects
D	covariance matrix of the random effects
invD	inverse of D
RinvD	matrix in prior for invD
alphas	regression coefficients in the imputation models
tau_imp	precision parameters of the residuals from imputation models
gamma_imp	intercepts in ordinal imputation models
delta_imp	increments of ordinal intercepts
other	additional parameters

For example:

monitor_params = c("analysis_main" = TRUE, "tau_y" = FALSE) would monitor the regression parameters betas and residual standard deviation sigma_y, but not the residual precision.

monitor_params = c(imps = TRUE) would monitor betas, tau_y, and sigma_y (because analysis_main = TRUE by default) as well as the imputed values.

See Also

traceplot, densplot, summary.JointAI, MC_error, GR_crit, jags.model, coda.samples, predict.JointAI

Examples

# NOT RUN {
mod1 <- lm_imp(y~C1 + C2 + M2, data = wideDF, n.iter = 100)
mod2 <- glm_imp(B1 ~ C1 + C2 + M2, data = wideDF,
                family = binomial(link = "logit"), n.iter = 100)
mod3 <- lme_imp(y ~ C1 + B2 + L1 + time, random = ~ time|id,
                data = longDF, n.iter = 500)


# }