Splitting your dataset
During the measure development process, it's important to conduct EFA and CFA on separate datasets because using the same dataset can lead to inflated model fit statistics. Instead, you can split your dataset in half, then use one half for the EFA and the other half for the CFA.
This exercise is part of the course
Factor Analysis in R
Exercise instructions
- Split the dataset in half using two sets of indices to determine which rows belong to each dataset.
- Use the first set of indices to create a dataset for your EFA, then use the second set for your CFA dataset.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Establish two sets of indices to split the dataset
N <- nrow(gcbs)
indices <- seq(1, ___)
indices_EFA <- sample(indices, floor((.5*___)))
indices_CFA <- indices[!(indices %in% ___)]
# Use those indices to split the dataset into halves for your EFA and CFA
gcbs_EFA <- gcbs[___, ]
gcbs_CFA <- gcbs[___, ]