Fitted 'SAEforest' object

An object of class SAEforest always includes point estimates of regionally disaggregated economic and inequality indicators and a MERFmodel element including information on the model fit for fixed effects as well as random effects. Optionally an SAEforestObject includes corresponding MSE estimates. In the case of mean estimates and aggregated covariate information, the SAEforestObject additionally includes an element, capturing the number of variables used in the weighting process from aggregated covariate information. For an object of class SAEforestObject, the following generic functions are applicable: print, plot, summary and summarize_indicators. Additionally selected generic functions of lme4 (fixef, getData, ranef, residuals, sigma, VarCorr) are directly applicable to an object of class SAEforest.

Value

Four components are always included in an SAEforest object. MSE_estimates and AdjustedSD are NULL except MSE results are requested. An element of NrCovar only exists for SAEforest objects produced by SAEforest_model with option aggData = TRUE.

MERFmodel

The included MERFmodel object comprises information on the model fit, details on the performed MERF algorithm as well as details on variance components. See below for an exact description of components.

Indicators

A data frame where the first column is the area-level identifier and additional columns are the indicators of interest. Note that objects from SAEforest_model only report the "Mean".

MSE_estimates

Only if MSE results requested. A data frame where the first column is the area-level identifier and additional columns are the MSE estimates for indicators of interest. Note that objects from SAEforest_model only report MSE values for the "Mean".

NrCovar

Only if means under aggregated covariate information are estimated, i.e. SAEforest_model with option aggData = TRUE. A list containing variable names of covariates used for the calculation of needed calibration weights for point estimates. See Krennmair et al. (2022a) for methodological details an explanations.

Details on object of MERFmodel:

Forest

A random forest of class ranger modelling fixed effects of the model.

EffectModel

A model of random effects of class merMod capturing structural components of MERFs and modeling random components.

RandomEffects

List element containing the values of random intercepts from EffectModel.

RanEffSD

Numeric value of standard deviation of random intercepts.

ErrorSD

Numeric value of standard deviation of unit-level errors.

VarianceCovariance

VarCorr matrix from EffectModel.

LogLik

Vector with numerical entries showing the loglikelihood of the MERF algorithm.

IterationsUsed

Numeric number of iterations used until convergence of the MERF algorithm.

OOBresiduals

Vector of OOB-residuals.

Random

Character specifying the random intercept in the random effects model.

ErrorTolerance

Numerical value to monitor the MERF algorithm's convergence.

initialRandomEffects

Numeric value or vector of initial specification of random effects.

MaxIterations

Numeric value specifying the maximal amount of iterations for the MERF algorithm.

call

The summarized function call producing the object.

data_specs

Data characteristics such as domain-specific sample sizes or number of out-of-sample areas.

data

Processed survey sample data.

Details

Note that the MERFmodel object is a composition of elements from a random forest of class ranger and a random effects model of class merMod. Thus, all generic functions are applicable to corresponding objects. For further details on generic functions see ranger and lmer as well as the examples below.

References

Krennmair, P., & Schmid, T. (2022). Flexible Domain Prediction Using Mixed Effects Random Forests. Journal of Royal Statistical Society: Series C (Applied Statistics) (forthcoming).

Krennmair, P., & Würz, N. & Schmid, T. (2022a). Analysing Opportunity Cost of Care Work using Mixed Effects Random Forests under Aggregated Census Data.

Krennmair, P., & Schmid, T & Tzavidis, Nikos. (2022b). The Estimation of Poverty Indicators Using Mixed Effects Random Forests. Working Paper.

See also

SAEforest_model, ranger, lmer

Examples

# \donttest{
# Loading data
data("eusilcA_pop")
data("eusilcA_smp")

income <- eusilcA_smp$eqIncome
X_covar <- eusilcA_smp[,-c(1,16,17,18)]

# Example 1:
# Calculating point estimates and discussing basic generic functions

model1 <- SAEforest_model(Y = income, X = X_covar, dName = "district",
                         smp_data = eusilcA_smp, pop_data = eusilcA_pop,
                         num.trees=50, mtry = 3)
#> Error in initializePtr(): function 'cholmod_factor_ldetA' not provided by package 'Matrix'

#SAEforest generics:

summary(model1)
#> Error in eval(expr, envir, enclos): object 'model1' not found
summarize_indicators(model1)
#> Error in eval(expr, envir, enclos): object 'model1' not found
residuals(model1)
#> Error in eval(expr, envir, enclos): object 'model1' not found
sigma(model1)
#> Error in eval(expr, envir, enclos): object 'model1' not found
# }