EVALUATING FACTOR INVARIANCE IN OBLIQUE SPACE: BASELINE DATA GENERATED FROM RANDOM NUMBERS.

Area of Science:

• Psychometrics
• Statistical Modeling

Background:

• Factor analysis is a common statistical technique.
• Oblique factor rotation is used when factors are expected to correlate.
• Understanding factor invariance is crucial for reliable analysis.

Purpose of the Study:

• To investigate the invariance of oblique factors under random data conditions.
• To determine the influence of sample size, number of variables, and number of extracted factors on oblique factor invariance.

Main Methods:

• The study employed random data simulations.
• Factor invariance was assessed across varying sample sizes (50, 100, 200).
• Analyses considered different numbers of variables (15, 30, 45) and extracted factors (5, 10).

Main Results:

• Oblique factor invariance demonstrated sensitivity to the tested parameters.
• Increasing sample size generally improved factor invariance.
• The number of variables and extracted factors also influenced the stability of oblique solutions.

Conclusions:

• The findings highlight the importance of adequate sample size and variable selection for stable oblique factor solutions.
• Researchers should carefully consider these parameters when conducting factor analyses.
• These results contribute to a better understanding of oblique factor rotation robustness.