mrp_onestep: Fits and tidies MRP outputs in one step

In kuriwaki/ccesMRPrun: Using MRP Models from Cleaned CCES and Census Data

Fits and tidies MRP outputs in one step

Description

Fits and tidies MRP outputs in one step

Usage

mrp_onestep(
  .formula,
  .data,
  poststrat_tgt,
  area_var = "cd",
  count_var = "count",
  weight_var = NULL,
  add_on = NULL,
  dtplyr = TRUE,
  new_levels = FALSE,
  allow_NA = FALSE,
  ...
)

Arguments

.formula	Formula in ⁠binary y ~ (1|x1) + (1|x2)⁠ form.
.data	Individual-level dataset
poststrat_tgt	The poststratification target. It must contain the column count, which is treated as the number of trials in the binomial model.
area_var	Character for the variable(s) that corresponds to the area to aggregate to.
count_var	A character string for the variable name for the population count in the poststrat_tgt dataframe. This will be renamed as if it is a trial count in the model. Defaults to "count".
weight_var	Character for the variable that corresponds to weights.
add_on	Any area-level data to be merged with the output, for example validation data
dtplyr	Whether to use a data.table/dtplyr backend for processing for slightly faster dataframe wrangling. Currently does not apply to anything within the function.
new_levels	If there are new levels in the poststrat table that do not have coefficients in the survey data, should there be an extrapolation or assignment to 0s? The answer should almost always be No in MRP.
allow_NA	A logical (TRUE or FALSE) indicating whether the summ_sims function should allow NAs in the cell-level estimate or break. The default is FALSE.
...	Arguments passed on to fit_brms_binomial .prior prior specification that can be interpreted by brms. The default is a standard normal prior, which is tighter than the brms default but has shown to have good prior posterior draws .cores Number of cores to uses .chains Number of chains to pass on fit_brms .iter Number of total iterations. .warmup Of the iterations, how much are burn-ins. Defaults to half. verbose Whether to show iteration messages .seed seed for randomization to pass into brm .backend The backend argument of brms. Currently only "cmdstanr" .threads The number of threads to do within-chain parallelization. Defaults to not using, which is NULL

Details

Combines fit_brms, poststrat_draws, and direct_est. See scatter_45 for options on visualization

Examples

## Not run: 
library(ccesMRPviz)
mrp_fit <- mrp_onestep(response ~ (1|educ) + (1|cd),
                       .data = cces_GA,
                       poststrat_tgt = acs_GA,
                       area_var = "cd",
                       count_var = "count",
                       weight_var = "weight_post",
                       add_on = elec_GA)

scatter_45(mrp_fit, clinton_vote, p_mrp_est,
           xlab = "Clinton Vote", ylab = "MRP Estimate")

## End(Not run)

kuriwaki/ccesMRPrun documentation built on Sept. 24, 2024, 2:15 a.m.