Comment on M. J. Greenwood's Simultaneity Bias in Migration Models: An Empirical Examination.
A discussion of the shortcomings of Greenwood's August 1975 article in [Demography]. Greenwood purports to examine empirically the importance of simultaneity bias in migration models. However, there is no such thing as an "empirical" examination of bias (unless one means some kind of Monte Carlo technique). Furthermore, Greenwood usually does not compare estimates produced by biased and unbiased techniques for the same specification, and focuses his discussion on significance levels rather than coefficient magnitudes. Other problems with the interpretation of results and definitions of the dependent and explanatory variables are noted. It is suggested that many of these problems could be avoided or mitigated through the use of individual-level, longitudinal data. 9 pp. Ref.