Estimating production functions using inputs to control for unobservables
TL;DR: Olley and Pakes as discussed by the authors show that when intermediate inputs (i.e., those inputs which are typically subtracted out in a value-added production function) can also solve this simultaneity problem, and discuss some potential benefits of expanding the choice set of proxies to include these inputs.
Abstract: Economists began relating output to inputs in the early 1800's. A large literature on estimating production functions has followed, in part because much of economic theory yields testable implications that are related to the technology and optimizing behaviour.1 Since at least as early as Marschak and Andrews (1944), applied researchers have worried about the potential correlation between input levels and the unobserved firm-specific productivity shocks in the estimation of production function parameters. The economics underlying this concern are intuitive. Firms that have a large positive productivity shock may respond by using more inputs. To the extent that this is true, ordinary least squares (OLS) estimates of production functions will yield biased parameter estimates, and, by implication, biased estimates of productivity. Many alternatives to OLS have been proposed, and we add to this set by extending Olley and Pakes (1996). They show the conditions under which an investment proxy controls for correlation between input levels and the unobserved productivity shock. Their approach has the advantage that, for many questions, it is no more difficult to implement than OLS. We show when intermediate inputs (those inputs which are typically subtracted out in a value-added production function) can also solve this simultaneity problem. We discuss some potential benefits of expanding the choice set of proxies to include these inputs.
Citations
More filters
TL;DR: The authors surveys and evaluates recent empirical work addressing the question of why businesses differ in their measured productivity levels, and lays out what I see are the major questions that research in the area should address going forward.
Abstract: Economists have shown that large and persistent differences in productivity levels across businesses are ubiquitous. This finding has shaped research agendas in a number of fields, including (but not limited to) macroeconomics, industrial organization, labor, and trade. This paper surveys and evaluates recent empirical work addressing the question of why businesses differ in their measured productivity levels. The causes are manifold, and differ depending on the particular setting. They include elements sourced in production practices -- and therefore over which producers have some direct control, at least in theory -- as well as from producers' external operating environments. After evaluating the current state of knowledge, I lay out what I see are the major questions that research in the area should address going forward. (JEL D24, G31, L11, M10, O30, O47)
2,380 citations
Posted Content•
TL;DR: In this article, the authors investigate the nature of selection and productivity growth using data from industries where they observe producer-level quantities and prices separately, and show that there are important differences between revenue and physical productivity.
Abstract: There is considerable evidence that producer-level churning contributes substantially to aggregate (industry) productivity growth, as more productive businesses displace less productive ones. However, this research has been limited by the fact that producer-level prices are typically unobserved; thus within-industry price differences are embodied in productivity measures. If prices reflect idiosyncratic demand or market power shifts, high "productivity" businesses may not be particularly efficient, and the literature's findings might be better interpreted as evidence of entering businesses displacing less profitable, but not necessarily less productive, exiting businesses. In this paper, we investigate the nature of selection and productivity growth using data from industries where we observe producer-level quantities and prices separately. We show there are important differences between revenue and physical productivity. A key dissimilarity is that physical productivity is inversely correlated with plant-level prices while revenue productivity is positively correlated with prices. This implies that previous work linking (revenue-based) productivity to survival has confounded the separate and opposing effects of technical efficiency and demand on survival, understating the true impacts of both. We further show that young producers charge lower prices than incumbents, and as such the literature understates the productivity advantage of new producers and the contribution of entry to aggregate productivity growth.
1,580 citations
TL;DR: In this article, the productivity gains from reducing tariffs on final goods and from reducing taxes on intermediate inputs are estimated. And they show that a 10 percentage point fall in input tariffs leads to a productivity gain of 12 percent for firms that import their inputs.
Abstract: This paper estimates the productivity gains from reducing tariffs on final goods and from reducing tariffs on intermediate inputs. Lower output tariffs can increase productivity by inducing tougher import competition, whereas cheaper imported inputs can raise productivity via learning, variety, and quality effects. We use Indonesian manufacturing census data from 1991 to 2001, which include plant-level information on imported inputs. The results show that a 10 percentage point fall in input tariffs leads to a productivity gain of 12 percent for firms that import their inputs, at least twice as high as any gains from reducing output tariffs. (JEL F12, F13, L16, O14, O19, O24)
1,303 citations
TL;DR: In this article, the authors examine some of the recent literature on the estimation of production functions and suggest an alternative approach that is based on the ideas in these papers, but does not suffer from the functional dependence problems and produces consistent estimates under alternative data generating processes for which the original procedures do not.
Abstract: This paper examines some of the recent literature on the estimation of production functions. We focus on techniques suggested in two recent papers, Olley and Pakes (1996) and Levinsohn and Petrin (2003). While there are some solid and intuitive identification ideas in these papers, we argue that the techniques can suffer from functional dependence problems. We suggest an alternative approach that is based on the ideas in these papers, but does not suffer from the functional dependence problems and produces consistent estimates under alternative data generating processes for which the original procedures do not.
1,209 citations
TL;DR: The authors used matched sampling techniques to analyze whether firms that start exporting become more productive, controlling for the self-selection into export markets, and found that the productivity gains are higher for firms exporting towards high income regions.
1,146 citations
References
More filters
TL;DR: In this article, the authors proposed a method to improve the performance of the system by using the information of the user's interaction with the system and the system itself, including the interaction between the two parties.
Abstract: В статье производится анализ агрегированной производственной функции, вводится аппарат, позволяющий различать движение вдоль такой функции от ее сдвигов. На основании сделанных в статье предположений делаются выводы о характере технического прогресса и технологических изменений. Существенное внимание уделяется вариантам применения концепции агрегированной производственной функции.
10,850 citations
TL;DR: In this paper, an empirical focus is on estimating the parameters of a production function for the equipment industry, and then using those estimates to analyze the evolution of plant-level productivity.
Abstract: Technological change and deregulation have caused a major restructuring of the telecommunications equipment industry over the last two decades. Our empirical focus is on estimating the parameters of a production function for the equipment industry, and then using those estimates to analyze the evolution of plant-level productivity. The restructuring involved significant entry and exit and large changes in the sizes of incumbents. Firms' choices on whether to liquidate, and on input quantities should they continue, depended on their productivity. This generates a selection and a simultaneity problem when estimating production functions. Our theoretical focus is on providing an estimation algorithm which takes explicit account of these issues. We find that our algorithm produces markedly different and more plausible estimates of production function coefficients than do traditional estimation procedures. Using our estimates we find increases in the rate of aggregate productivity growth after deregulation. Since we have plant-level data we can introduce indices which delve deeper into how this productivity growth occurred. These indices indicate that productivity increases were primarily a result of a reallocation of capital towards more productive establishments.
3,657 citations
TL;DR: In this article, a variable aleatoire (X,Z) dans #7B-R P ×#7b-R q is considered, and an estimateur generalisant l'estimateur des moindres carres ordinaires en inserant des estimateurs non parametriques de la regression dans la projection orthogonale non lineaire sur Z is constructed.
Abstract: On considere une variable aleatoire (X,Z) dans #7B-R P ×#7B-R q . On construit un estimateur generalisant l'estimateur des moindres carres ordinaires en inserant des estimateurs non parametriques de la regression dans la projection orthogonale non lineaire sur Z
2,393 citations
TL;DR: In this article, the estimation of Cobb-Douglas production functions using panel data covering a large sample of companies observed for a small number of time periods was considered, and the additional instruments used in the extended GMM estimator yield much more reasonable parameter estimates.
Abstract: This paper considers the estimation of Cobb-Douglas production functions using panel data covering a large sample of companies observed for a small number of time periods. GMM estimatorshave been found to produce large finite-sample biases when using the standard first-differenced estimator. These biases can be dramatically reduced by exploiting reasonable stationarity restrictions on the initial conditions process. Using data for a panel of R&Dperforming US manufacturing companies we find that the additional instruments used in our extended GMM estimator yield much more reasonable parameter estimates.
2,097 citations
Posted Content•
TL;DR: In this paper, the authors quantified the effect of prior exporting experience on the decisions of Colombian manufacturing plants to participate in foreign markets and developed a dynamic discrete-choice model of exporting behavior that separates the roles of profit heterogeneity and sunk entry costs in explaining plants' exporting status.
Abstract: Recent theoretical models of entry predict that, in the presence of sunk costs, current market participation is affected by prior experience This paper quantifies the effect of prior exporting experience on the decisions of Colombian manufacturing plants to participate in foreign markets It develops a dynamic discrete-choice model of exporting behavior that separates the roles of profit heterogeneity and sunk entry costs in explaining plants' exporting status Sunk costs are found to be significant and prior export experience is shown to increase the probability of exporting by as much as sixty percentage points Copyright 1997 by American Economic Association
1,990 citations