A common problem with micro-level analysis is that capital stock data is missing. Typically, a feasible measure of capital is calculated by accumulating investment flows from an initial value of the capital stock. As the time dimension of most disaggregated data is rather short, the choice of this initial value can have significant effects on the resulting capital estimates. Most empirical studies impute the initial value using a single arbitrary proxy. In this paper, we propose a panel data framework that assigns weighting coefficients to multiple proxy variables. We conduct a series of Monte Carlo experiments to test the performance of the proposed method and apply the method to a U.S. manufacturing dataset. The results suggest that our method improves the approximation of the capital stock and thus in turn reduces the bias in the production function estimation.

Although a realistic characterization of the production function is critical to macroeconomic analysis, estimating the function's characteristics is hampered by both data limitations and methodological difficulties. In this paper, I develop a new empirical strategy for estimating the CES production function with biased technical change. The proposed method extends the control function approach to the CES specification to address endogeneity concerns and is able to retrieve sector-specific and time-varying estimates of technical change. Using data from U.S. manufacturing industries, I find evidence that (i) the production technology exhibits nonincreasing returns to scale, (ii) the elasticity of substitution between capital and labor is below unity, and (iii) technical change is generally labor-augmenting along the balanced growth path.

A problem in the empirical production analysis at the firm-level is that the values of capital are missing in the data. Most empirical studies impute initial capital according to some ad hoc criteria and then estimate the parameters of production function based on these imputed values. This paper proposes a generalized method to deal with the missing initial capital problem.

Dans cet article, nous développons une stratégie empirique basée sur les modèles d’évaluation, nous permettant de montrer (i) qu’il existe un coût fixe d’entrée à l’exportation pour les entreprises françaises et (ii) que le niveau de ce coût est affecté de façon significative par la productivité de l’entreprise. Avec ces résultats empiriques, nous généralisons le modèle de Melitz [2003] en considérant que les coûts d’entrée auxquels les entreprises font face sur le marché de l’exportation sont hétérogènes. Notre modèle théorique met en lumière le rôle de cette hétérogénéité et son lien avec la productivité des entreprises. En particulier, nous montrons l’importance de la prise en compte de ces coûts fixes hétérogènes afin de mieux évaluer le mécanisme d’auto-sélection des entreprises sur le marché de l’exportation.