In today’s episode Greg & Patrick discuss the causes, consequences, and potential solutions associated with negative residual variances in factor analyses, a condition commonly called a Heywood case. Along the we way they also discuss vegetarian pepperoni, Jaws Part 2, coffin seat belts, balancing a ship, bad puns, sterilizing needles, dead canaries, hitchhikers, legal depositions, boxes of geodes, knowing what time it is, and models that give you the finger.
Boomsma, A., & Hoogland, J. J. (2001). The robustness of LISREL modeling revisited. Structural equation models: Present and future. A Festschrift in honor of Karl Jöreskog, 2, 139-168.
Chen, F., Bollen, K. A., Paxton, P., Curran, P. J., & Kirby, J. B. (2001). Improper solutions in structural equation models: Causes, consequences, and strategies. Sociological Methods & Research, 29, 468-508.
Cooperman, A. W., & Waller, N. G. (2021). Heywood you go away! Examining causes, effects, and treatments for Heywood cases in exploratory factor analysis. Psychological Methods.
Heywood, H. B. (1931). On finite sequences of real numbers. Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character, 134(824), 486-501.
Kenny, D. A. (1979). Correlation and causality. New York: Wiley.
Kolenikov, S., & Bollen, K. A. (2012). Testing negative error variances: Is a Heywood case a symptom of misspecification?. Sociological Methods & Research, 41, 124-167.
Rindskopf, D. (1984). Structural equation models: Empirical identification, Heywood cases, and related problems. Sociological Methods & Research, 13, 109-119.