A proposed method to estimate dynamic panel models when either N or T or both are not large

Traditionally the bias of an estimator has been reduced asymptotically to zero by enlarging data panel dimensions N or T or both. This research proposes a novel econometric modelling method to separate and measure the bias of an estimator without altering data panel dimensions. This is done by recursively decomposing its bias in systematic and nonsystematic parts. This novel method addresses the bias of an estimator as a type of asymptotic serial correlation problem. Once this method disentangles bias components it could provide consistent estimators and adequate statistic inference. This recursive bias approach is missed from the current bias literature. This novel method results do not cast doubt about the asymptotic bias approach conclusions, but made them incomplete. Monte Carlo simulations find consistent sample estimators asymptotic convergence with population estimators by enlarging the sample size. In these simulations the population estimator value is provided beforehand the simulation begins. The mean advantage of the alternative recursive estimator bias approach is that the sample estimator recursively converges with population estimators without enlarging sample size. Importantly this novel method avoids researcher bias criteria, which consist on an arbitrary a priori population estimator value selection.