Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Entire DC Network
Specification Testing In Panel Data With Instrumental Variables, Gilbert E. Metcalf
Specification Testing In Panel Data With Instrumental Variables, Gilbert E. Metcalf
Gilbert E. Metcalf
I show that specification tests for correlated fixed effects developed by Hausman and Taylor extend in an analogous way to panel data sets with endogenous regressors. Given panel data, different sets of instrumental variables can be used to construct the test. For a simple class of models, the test in many cases is asymptotically more efficient if an incomplete set of instruments is used. However, in small samples one may do better using the complete set of instruments. Monte Carlo results demonstrate the likely gains for different assumptions about the degree of between and within variance in the data.
Can Irreversibility Explain The Slow Diffusion Of Energy Saving Technologies? (With Kevin Hassett), Gilbert E. Metcalf
Can Irreversibility Explain The Slow Diffusion Of Energy Saving Technologies? (With Kevin Hassett), Gilbert E. Metcalf
Gilbert E. Metcalf
A model was developed on the effects of irreversibility on home improvement behavior. It is also considered whether it may be helpful in shedding light on the slow diffusion of new energy technologies. This work has been criticized for being of little value in studying the high discount rates applied by consumers to home-improvement purchases. It is proven that the model can generate predicted hurdle rates as high as those estimated in the literature, and thus solve the energy paradox.
Specification Testing In Panel Data With Instrumental Variables, Gilbert E. Metcalf
Specification Testing In Panel Data With Instrumental Variables, Gilbert E. Metcalf
Gilbert E. Metcalf
I show that specification tests for correlated fixed effects developed by Hausman and Taylor extend in an analogous way to panel data sets with endogenous regressors. Given panel data, different sets of instrumental variables can be used to construct the test. For a simple class of models, the test in many cases is asymptotically more efficient if an incomplete set of instruments is used. However, in small samples one may do better using the complete set of instruments. Monte Carlo results demonstrate the likely gains for different assumptions about the degree of between and within variance in the data.