Nonparametric estimation of returns to scale using input distance functions: an application to large US banks
We derive new measures of returns to scale based on input distance functions (IDFs) and estimate them using nonparametric regression methods. In contrast to the cost function approach, the IDF does not require input prices which are usually unavailable or measured imprecisely. In addition, we can ac...
- Autores:
-
Restrepo-Tobón, Diego
Kumbhakar, Subal C.
- Tipo de recurso:
- Fecha de publicación:
- 2015
- Institución:
- Universidad EAFIT
- Repositorio:
- Repositorio EAFIT
- Idioma:
- eng
- OAI Identifier:
- oai:repository.eafit.edu.co:10784/7613
- Acceso en línea:
- http://hdl.handle.net/10784/7613
- Palabra clave:
- Nonparametric regression
Returns to scale
Distance functions
Banks
- Rights
- License
- restrictedAccess
| Summary: | We derive new measures of returns to scale based on input distance functions (IDFs) and estimate them using nonparametric regression methods. In contrast to the cost function approach, the IDF does not require input prices which are usually unavailable or measured imprecisely. In addition, we can account for equity and physical capital in the IDF. These variables are either excluded from the analysis (especially in a cost function approach) or treated as quasi-fixed inputs, because their prices are not readily available. In our application, we use data for bank holding companies and large commercial banks in the U.S. from 2000 to 2010. We find that although some of these institutions enjoy increasing returns to scale, scale economies are economically small. Thus, concerns about potential cost increases arising from breaking up large banking organizations seem exaggerated, especially from the scale economies point of view. |
|---|