compare_pred {saeTrafo}

Compare predictions of model objects

Description

Function compare_pred is a generic function used to compare predictions of two model objects.

Method compare_pred.saeTrafo compares predictions of two saeTrafo objects or a saeTrafo object and a emdi object.

Usage

compare_pred(object1, object2, MSE = FALSE, ...)

## S3 method for class 'saeTrafo'
compare_pred(object1, object2, MSE = FALSE, ...)

Arguments

object1

an object of type "saeTrafo".

object2

an object of type "saeTrafo" or "emdi" (emdiObject).

MSE

optional logical. If TRUE, MSE estimates are returned. Defaults to FALSE and than point estimates are returned.

...

further arguments passed to or from other methods.

Value

Data frame containing the point estimates or the MSE estimates (if MSE is set to TRUE) of both objects. If column names are duplicated, the suffixes "_1" and "_2" are added to their names. "_1" and "_2" standing for object1 and object2, respectively.

See Also

emdi, NER_Trafo, saeTrafoObject

Examples

# Example comparing two saeTrafo objects


# Load Data
data("eusilcA_smp")
data("pop_area_size")
data("pop_mean")
data("pop_cov")

# Nested error regression model 1
NER_model_1 <- NER_Trafo(fixed = eqIncome ~ gender + eqsize + cash +
                         self_empl + unempl_ben + age_ben + surv_ben +
                         sick_ben + dis_ben + rent + fam_allow +
                         house_allow + cap_inv + tax_adj,
                         smp_domains = "district",
                         pop_area_size = pop_area_size,
                         pop_mean = pop_mean, pop_cov = pop_cov,
                         smp_data = eusilcA_smp, MSE = TRUE)

# Nested error regression model 2
NER_model_2 <- NER_Trafo(fixed = eqIncome ~ gender + eqsize + cash +
                         self_empl + unempl_ben + age_ben + surv_ben,
                         smp_domains = "district",
                         pop_area_size = pop_area_size,
                         pop_mean = pop_mean, pop_cov = pop_cov,
                         smp_data = eusilcA_smp, MSE = TRUE)

# Generate a data frame for the comparison of point estimates
compare_pred(NER_model_1, NER_model_2)

# Generate a data frame for the comparison of MSE estimates
compare_pred(NER_model_1, NER_model_2, MSE = TRUE)