Carlo experiments.
The between period (BP) estimates on levels for the original and the reverse
regression give virtually the same input elasticity for materials. For capital, we find
substantial deviations between the two sets of BP estimators, which may indicate
that measurement errors or disturbances have period specific, or strongly serially
correlated, components.
Finally, we find that GMM estimates based on the equation in levels are more
precise than those based on the equation in differences. Deducting period means
from levels to compensate for non-stationarity of the latent regressor, give estimates
for the level equation which are less precise and more sensitive to the choice of in-
strument set than those operating on untransformed levels. On the other hand, this
kind of transformations of level variables may be needed to compensate for period
effects, mis-specified dynamics, or non-stationarity of the variables, in particular
for the capital input variable. It should come as no surprise that the adjustment
of material input is far easier to model within the framework considered than is
capital.
27
More intriguing information
1. Opciones de política económica en el Perú 2011-20152. Novelty and Reinforcement Learning in the Value System of Developmental Robots
3. Response speeds of direct and securitized real estate to shocks in the fundamentals
4. Linkages between research, scholarship and teaching in universities in China
5. The name is absent
6. The name is absent
7. Has Competition in the Japanese Banking Sector Improved?
8. An Interview with Thomas J. Sargent
9. Wounds and reinscriptions: schools, sexualities and performative subjects
10. Studying How E-Markets Evaluation Can Enhance Trust in Virtual Business Communities