seminrExtras (version 0.9.0)

assess_cvpat_compare: SEMinR function to compare CVPAT loss of two models

Description

`assess_cvpat_compare` conducts a CVPAT significance test of loss between two models.

Usage

assess_cvpat_compare(
  established_model,
  alternative_model,
  testtype = "two.sided",
  nboot = 2000,
  seed = 123,
  technique = predict_DA,
  noFolds = NULL,
  reps = NULL,
  cores = NULL
)

Value

A matrix of the estimated loss and results of significance testing.

Arguments

established_model

The base seminr model for CVPAT comparison.

alternative_model

The alternate seminr model for CVPAT comparison.

testtype

Either "two.sided" (default) or "greater".

nboot

The number of bootstrap subsamples to execute (defaults to 2000).

seed

The seed for reproducibility (defaults to 123).

technique

predict_EA or predict_DA (default).

noFolds

Number of folds for k-fold cross validation.

reps

Number of repetitions for cross validation.

cores

Number of cores for parallelization.

References

Sharma, P. N., Liengaard, B. D., Hair, J. F., Sarstedt, M., & Ringle, C. M. (2022). Predictive model assessment and selection in composite-based modeling using PLS-SEM: extensions and guidelines for using CVPAT. European journal of marketing, 57(6), 1662-1677.

Liengaard, B. D., Sharma, P. N., Hult, G. T. M., Jensen, M. B., Sarstedt, M., Hair, J. F., & Ringle, C. M. (2021). Prediction: coveted, yet forsaken? Introducing a cross‐validated predictive ability test in partial least squares path modeling. Decision Sciences, 52(2), 362-392.

Examples

# Load libraries
library(seminr)
library(seminrExtras)

# Create measurement model ----
corp_rep_mm_ext <- constructs(
 composite("QUAL", multi_items("qual_", 1:8), weights = mode_B),
 composite("PERF", multi_items("perf_", 1:5), weights = mode_B),
 composite("CSOR", multi_items("csor_", 1:5), weights = mode_B),
 composite("ATTR", multi_items("attr_", 1:3), weights = mode_B),
 composite("COMP", multi_items("comp_", 1:3)),
 composite("LIKE", multi_items("like_", 1:3))
)

alt_mm <- constructs(
 composite("QUAL", multi_items("qual_", 1:8), weights = mode_B),
 composite("PERF", multi_items("perf_", 1:5), weights = mode_B),
 composite("CSOR", multi_items("csor_", 1:5), weights = mode_B),
 composite("COMP", multi_items("comp_", 1:3)),
 composite("LIKE", multi_items("like_", 1:3))
)

# Create structural model ----

corp_rep_sm_ext <- relationships(
 paths(from = c("QUAL", "PERF", "CSOR", "ATTR"), to = c("COMP", "LIKE"))
)
alt_sm <- relationships(
 paths(from = c("QUAL", "PERF", "CSOR"), to = c("COMP", "LIKE"))
)

# Estimate the model ----
established_model <- estimate_pls(
 data = corp_rep_data,
 measurement_model = corp_rep_mm_ext,
 structural_model  = corp_rep_sm_ext,
 missing = mean_replacement,
 missing_value = "-99")

alternative_model <- estimate_pls(
 data = corp_rep_data,
 measurement_model = alt_mm,
 structural_model  = alt_sm,
 missing = mean_replacement,
 missing_value = "-99")

# Function to compare the Loss of two models
assess_cvpat_compare(established_model,
                    alternative_model ,
                    testtype = "two.sided",
                    nboot = 20,
                    seed = 123,
                    technique = predict_DA,
                    noFolds = 5,
                    reps = 1,
                    cores = 1)