Half day short course (Monday, July 19; 9:00AM-12:30PM US Eastern)
If our models were perfectly valid and our variables came from normal distributions, the maximum likelihood and related estimators that dominate SEM software would be hard to beat. In reality, however, such structural and distributional assumptions are rarely if ever satisfied. This workshop will discuss more robust estimators that better represent real world conditions. The Model Implied Instrumental Variable, Two Stage Least Squares (MIIV-2SLS) estimator is more robust to the approximate nature of our models and are asymptotically distribution free. In addition, they can test equation level fit so as to better localize model misspecification. The workshop will give an overview of the free R package MIIVsem. We will introduce the key ideas behind MIIV-2SLS estimation; we will show how MIIVsem automates the selection of MIIVs, the estimation of coefficients and standard errors, and provides overidentification tests for equations. These and other features will be introduced and illustrated with a variety of empirical examples. We will provide instructions on downloading R and MIIVsem in advance of the workshop so that those participants who would like to practice with the program can do so. No prior knowledge of R or MIIVsem is assumed.
About the Instructors
Ken Bollen is the H.R. Immerwahr Distinguished Professor in the Department of Psychology and Neuroscience and Department of Sociology at the University of North Carolina at Chapel Hill. He is a member of the L.L. Thurstone Psychometric Laboratory that is part of the Quantitative Psychology Program at UNC. He also heads the Method Unit and is a Fellow at the Carolina Population Center. Structural equation models, confirmatory factor analysis, longitudinal and time series analysis, and measurement are his major research areas. Among his honors in recognition of his research are a 2019 honorary doctorate from Uppsala University (Uppsala, Sweden); the Career Award for Lifetime Achievement from the Psychometric Society; and the 2000 Paul F. Lazarsfeld Memorial Award for Distinguished Contributions in the Field of Sociological Methodology from the American Sociological Association (Methods Section). Google Scholar registers over 100,000 citations to his publications.
Zack Fisher is the lead programmer of the MIIVsem package. He is a National Institute of Health T32 Postdoctoral Fellow at the Carolina Population Center. His research focuses on methods development in the areas of time series analysis and structural equation modeling.