|
Activity Number:
|
507
- Business, Time Series, and Spatial Analysis Methods
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #313128
|
|
|
Title:
|
Heterogeneity in Firms: A Proxy Variable Approach for Quantile Production Functions
|
|
Author(s):
|
Justin Doty* and Suyong Song
|
|
Companies:
|
University of Iowa and University of Iowa
|
|
Keywords:
|
Production functions;
heterogeneous elasticity;
nonlinear quantile regression
|
|
Abstract:
|
We propose a new approach to estimate firm-level production functions of which output elasticities are heterogeneous. This paper extends the proxy variable approach for estimating production functions to the conditional quantiles of firm production. Production function parameters are identified by conditional quantile restrictions and estimated using the implied unconditional sample moment restrictions. We show that this method allows us to capture heterogeneity in output elasticities along the firm-size distribution that would not be estimated in conditional mean models. We provide small-sample evidence in a Monte Carlo study to show that this approach is robust compared to other production function estimators. The method is applied to the Chilean manufacturing industry.
|
Authors who are presenting talks have a * after their name.
