SEMinR Lecture Series - Analyzing Categorical Predictors
SEMinR Lecture Series
This session is focused on how to perform moderation analysis using SEMinR in Cran R.
Categorical Predictor Variables using SEMinR in R
- The objective is to assess whether Country has an impact on Customer Loyalty.
- Country is a categorical variable in the study with three countries China, Pakistan, and Italy.
- Country is not added into the model directly. Since, it is a categorical variable, first the variable is dummy coded. Each Country will become a separate variable.
- In this case Two categories (Countries) will be added in the model estimation. Whereas the third country will serve as a reference category.
Create Dummy Variables in R
- Dummy variables are created when the exogenous variable is categorical in nature.
- Each category is transformed into a dummy variable.
- To create dummy variables in R, install fastDummies package
library(seminr) library(fastDummies) # Load the Data datas <- read.csv(file = "Data.csv", header = TRUE, sep = ",") # Create dummy variables datas <- dummy_cols(datas, select_columns = "Country") head(datas) # Create measurement model simple_mm <- constructs( composite("Loyalty", multi_items("CL", 1:6)), composite("Pakistan", single_item("Country_2")), composite("Italy", single_item("Country_3"))) # Create structural model simple_sm <- relationships( paths(from = c("Pakistan", "Italy"), to = "Loyalty")) # Estimate the model simple_model <- estimate_pls(data = datas, measurement_model = simple_mm, structural_model = simple_sm, missing = mean_replacement, missing_value = "-99") # Summarize the model results summary_simple <- summary(simple_model) summary_simple # Bootstrap the model on the PLS Estimated Model boot_model <- bootstrap_model( seminr_model = simple_model, nboot = 5000, cores = parallel::detectCores(), seed = 123) # Store the summary of the bootstrapped model # alpha sets the specified level for significance, i.e. 0.05 # Inspect the bootstrapped structural paths summary_boot$bootstrapped_paths
Hair Jr, J. F., Hult, G. T. M., Ringle, C. M., Sarstedt, M., Danks, N. P., & Ray, S. (2021). Partial Least Squares Structural Equation Modeling (PLS-SEM) Using R: A Workbook.
The tutorials on SEMinR are based on the mentioned book. The book is open source and available for download under this link.