Instrumental Variables

A frequent problem in the estimation of linear regression models is that the predictors are correlated with the error term contained in the regression equation. To obtain consistent estimates of the regression coefficients even in this case, econometricians typically use third variables - called Instrumental Variables or just Instruments (IVs) - to compute the regression coefficients. In this project, we use this IV regression method to estimate the parameters of different types of structural equation models (e.g., latent growth models, multi-level structural equation models, and so on) and investigate the statistical properties of the method for thes models.

Representative publications:

Nestler, S. (2014). How the 2SLS/IV estimator can handle equality constraints in structural equation models: A system-of-equations approach. British Journal of Mathematical and Statistical Psychology, 67, 353-369.

Nestler, S. (2015). Using Instrumental Variables to estimate the parameters in unconditional and conditional second-order latent growth models. Structural Equation Modeling, 22, 461-473.