Production Function Estimation in Stata using Inputs to Control for Unobservables

Petrin, Amil; Poi, Brian P.; Levinsohn, James

doi:10.1177/1536867x0400400202

Cited by 314 publications

(181 citation statements)

References 5 publications

Supporting

Mentioning

175

Contrasting

Unclassified

Order By: Relevance

“…7 The approach discussed above combines fixed-effects estimation and within-firm productivity comparison. It relies on the observed 3 The LP method can be implemented by using Stata command (Petrin et al, 2004). 4 Strictly, the rate of return is r = e b − 1.…”

Section: Methodsmentioning

confidence: 99%

Economic transition, higher education and worker productivity in China

Fleisher

et al. 2011

Journal of Development Economics

120

View full text Add to dashboard Cite

a b s t r a c t JEL classification: O15 J31 J24 D24 Keywords: Productivity Returns to education Marginal product Firm China TransitionWe investigate the role of education on worker productivity and firms' total factor productivity using a panel of firm-level data from China. We estimate the returns to education by calculating the marginal productivity of workers of different education levels based on estimates of the firm-level production function. We also estimate how the education level of workers and CEO contributes to firms' total factor productivity. Estimated marginal products are much higher than wages, and the gap is larger for highly educated workers. Our estimate shows that an additional year of schooling raises marginal product by 30.1%, and that CEO's education increases TFP for foreign-invested firms. Estimates vary substantially across ownership classes, the effect of schooling on productivity being highest in foreign-invested firms. We infer that market mechanisms contribute to a more efficient use of human capital within firms.

show abstract

Section: Methodsmentioning

confidence: 99%

Economic transition, higher education and worker productivity in China

Fleisher

et al. 2011

Journal of Development Economics

120

View full text Add to dashboard Cite

show abstract

“…As long as this function exhibits monotonicity, we can invert it to obtain x it = g À1 (K it , M it ). We estimate this from our data using Levinsohn and Petrin's revenue-based generalized method of moments estimator, as described by Petrin, Poi, and Levinsohn (2004):…”

Section: (B) Empirical Analysismentioning

confidence: 99%

Does Freer Trade Really Lead to Productivity Growth? Evidence from Africa

et al. 2016

View full text Add to dashboard Cite

Theory predicts that trade liberalization should raise average total factor productivity (TFP) among manufacturing firms. However, this is a generic prediction and depends on maintained assumptions about industries, factor markets, and trade patterns that may not fit well for developing countries. Using firm-level data from Ghana, Kenya, and Tanzania during the 1990s, a period of fairly rapid trade policy liberalization, we estimate productivity effects of trade. Our analysis confirms the well-known association between export intensity and higher productivity of the firm; however, the evidence for ''learning by exporting," or an increase in productivity associated with greater exports, is mixed, with several instances of negative average TFP growth among exporters. Our analysis indicates that such declines are likely attributable to the effects of lower external tariffs, because the firm-level productivity margin below which exporting is unprofitable moves down as the external tariff rate is reduced. We also find that sales to the rest of the world and sales to other African economies have differential effects on productivity growth rates, and that for country-specific reasons, these effects are not uniform. Controlling for initial productivity and the destination of exports (within or outside Africa) helps us understand why in some cases, export participation is associated with negative rates of TFP growth.

show abstract

“…To deal with this problem, we conduct regression of the production function according to the method of Levinsohn and Petrin (2003) and Pertin, Poi, and Levinsohn (2004). In this regression, we substitute the invested capital of the ASI for K and total employees of the ASI for L. We calculate the value of Y from the gross value of output of the ASI minus the total input of the ASI.…”

Section: Empirical Analysismentioning

confidence: 99%