Estimating Production Functions Using Inputs to Control for Unobservables

55 Pages Posted: 3 Aug 2000 Last revised: 15 May 2022

See all articles by James A. Levinsohn

James A. Levinsohn

University of Michigan; National Bureau of Economic Research (NBER)

Amil Petrin

University of Minnesota - Duluth; National Bureau of Economic Research (NBER)

Date Written: August 2000

Abstract

We introduce a new method for conditioning out serially correlated unobserved shocks to the production technology by building ideas first developed in Olley and Pakes (1996). Olley and Pakes show how to use investment to control for correlation between input levels and the unobserved firm-specific productivity process. We prove that like investment, intermediate inputs (those inputs which are typically subtracted out in a value-added production function) can also solve this simultaneity problem. We highlight three potential advantages to using an intermediate inputs approach relative to investment. Our results indicate that these advantages are empirically important.

Suggested Citation

Levinsohn, James A. and Petrin, Amil, Estimating Production Functions Using Inputs to Control for Unobservables (August 2000). NBER Working Paper No. w7819, Available at SSRN: https://ssrn.com/abstract=238143

James A. Levinsohn (Contact Author)

University of Michigan ( email )

611 Tappan Street
Ann Arbor, MI 48109-1220
United States
734-763-2319 (Phone)
734-764-8063 (Fax)

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Amil Petrin

University of Minnesota - Duluth ( email )

1049 University Drive
Duluth, MN 55812
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States