getSmoothed: Extract smoothed estimates.

In SUMMER: Small-Area-Estimation Unit/Area Models and Methods for Estimation in R

Extract smoothed estimates.

Description

Extract smoothed estimates.

Usage

getSmoothed(
  inla_mod,
  nsim = 1000,
  weight.strata = NULL,
  weight.frame = NULL,
  verbose = FALSE,
  mc = 0,
  include_time_unstruct = FALSE,
  CI = 0.95,
  draws = NULL,
  save.draws = FALSE,
  include_subnational = TRUE,
  ...
)

Arguments

inla_mod	output from smoothDirect or smoothCluster
nsim	number of simulations, only applicable for the cluster-level model. The smooth direct model always draws 1e5 samples from the marginal distribution since the computation is faster.
weight.strata	a data frame with two columns specifying time and region, followed by columns specifying proportion of each strata for each region. This argument specifies the weights for strata-specific estimates on the probability scale.
weight.frame	a data frame with three columns, years, region, and the weight of each frame for the corresponding time period and region. This argument specifies the weights for frame-specific estimates on the logit scale. Notice this is different from weight.strata argument.
verbose	logical indicator whether to print progress messages from inla.posterior.sample.
mc	number of monte carlo draws to approximate the marginal prevalence/hazards for binomial model. If mc = 0, analytical approximation is used. The analytical approximation is invalid for hazard modeling with more than one age groups.
include_time_unstruct	Indicator whether to include the temporal unstructured effects (i.e., shocks) in the smoothed estimates from cluster-level model. The argument only applies to the cluster-level models (from smoothCluster). Default is FALSE which excludes all unstructured temporal components. If set to TRUE all the unstructured temporal random effects will be included. Alternatively, if this is specified as a vector of subset of year labels (as in the year_label argument), only the unstructured terms in the corresponding time periods will be added to the prediction.
CI	Desired level of credible intervals
draws	Posterior samples drawn from the fitted model. This argument allows the previously sampled draws (by setting save.draws to be TRUE) be used in new aggregation tasks.
save.draws	Logical indicator whether the raw posterior draws will be saved. Saved draws can be used to accelerate aggregations with different weights.
include_subnational	logical indicator whether to include the spatial and space-time interaction components in the smoothed estimates. If set to FALSE, only the main temporal trends are returned.
...	Unused arguments, for users with fitted object from the package before v1.0.0, arguments including Amat, year_label, and year_range can still be specified manually.

Value

A data frame or a list of data frames of S3 class SUMMERproj, which contains the smoothed estimates.

Author(s)

Zehang Richard Li

See Also

plot.SUMMERproj

Examples

## Not run: 
years <- levels(DemoData[[1]]$time)

# obtain direct estimates
data <- getDirectList(births = DemoData, 
years = years,  
regionVar = "region", timeVar = "time", 
clusterVar = "~clustid+id", 
ageVar = "age", weightsVar = "weights", 
geo.recode = NULL)
# obtain direct estimates
data_multi <- getDirectList(births = DemoData, years = years,
  regionVar = "region",  timeVar = "time", clusterVar = "~clustid+id",
  ageVar = "age", weightsVar = "weights", geo.recode = NULL)
data <- aggregateSurvey(data_multi)

#  national model
years.all <- c(years, "15-19")
fit1 <- smoothDirect(data = data, Amat = NULL, 
  year_label = years.all, year_range = c(1985, 2019), 
  rw = 2, is.yearly=FALSE, m = 5)
out1 <- getSmoothed(fit1)
plot(out1, is.subnational=FALSE)

#  subnational model
fit2 <- smoothDirect(data = data, Amat = mat, 
  year_label = years.all, year_range = c(1985, 2019), 
  rw = 2, is.yearly=TRUE, m = 5, type.st = 4)
out2 <- getSmoothed(fit2)
plot(out2, is.yearly=TRUE, is.subnational=TRUE)



## End(Not run)

SUMMER documentation built on July 8, 2022, 9:05 a.m.