Coping with unobservables in estimating production functions: An example with US banking data

This paper (i) derives a number of properties of a newly specified multi-input-single-output (MISO) production function with a derived error term, and (ii) using iteratively rescaled generalized least squares, presents estimates of the cross-sectionally varying coefficients of a multi-input-multi-ou...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Swamy A.V.B. Paravastu, Peter von zur Muehlen, I-Lok Chang
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
T
Acceso en línea:https://doaj.org/article/17a0a8ceb2b640bb973fd2c8e2538cbd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:This paper (i) derives a number of properties of a newly specified multi-input-single-output (MISO) production function with a derived error term, and (ii) using iteratively rescaled generalized least squares, presents estimates of the cross-sectionally varying coefficients of a multi-input-multi-output (MIMO) production function with a derived error term based on newly derived conditions for estimating the total effects of its regressors on its dependent variable, when an unknown number of unobserved inputs is potentially involved in production. The results indicate that for the years 2008, 2009, and 2010, the coefficient estimates do not contain simultaneous-equations biases, bank heterogeneity is not pronounced, and non-transaction accounts turn out to be the dominant input.