Estimating dynamic spatial panel data models with endogenous regressors using synthetic instruments

Abstract The paper applies synthetic instruments, initially developed for cross-sectional regression, to estimate dynamic spatial panel data models. These have two main advantages. First, instruments correlated with endogenous variables and yet independent of the errors are difficult find. Not only normally exogenous, but they usually strongly variables, thus help avoid problem weak instruments. Secondly, reduce instrumental proliferation, which is a common result standard methods avoiding endogeneity bias. As demonstrated by Monte Carlo simulation, instrument proliferation causes bias in Sargan–Hansen J test statistic, an important indicator validity hence estimation consistency. It also associated downward parameter error estimates. shows results applying across variety different specifications generating processes, it illustrates method real leading more reliable inference causal impacts on level employment London districts.