Home > Research > Publications & Outputs > Globally flexible functional forms

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Globally flexible functional forms: the neural distance function

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Globally flexible functional forms: the neural distance function. / Michaelides, Panayotis G.; Vouldis, Angelos T.; Tsionas, Michael.
In: European Journal of Operational Research, Vol. 206, No. 2, 10.2010, p. 456-469.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Michaelides, PG, Vouldis, AT & Tsionas, M 2010, 'Globally flexible functional forms: the neural distance function', European Journal of Operational Research, vol. 206, no. 2, pp. 456-469. https://doi.org/10.1016/j.ejor.2010.02.013

APA

Michaelides, P. G., Vouldis, A. T., & Tsionas, M. (2010). Globally flexible functional forms: the neural distance function. European Journal of Operational Research, 206(2), 456-469. https://doi.org/10.1016/j.ejor.2010.02.013

Vancouver

Michaelides PG, Vouldis AT, Tsionas M. Globally flexible functional forms: the neural distance function. European Journal of Operational Research. 2010 Oct;206(2):456-469. doi: 10.1016/j.ejor.2010.02.013

Author

Michaelides, Panayotis G. ; Vouldis, Angelos T. ; Tsionas, Michael. / Globally flexible functional forms : the neural distance function. In: European Journal of Operational Research. 2010 ; Vol. 206, No. 2. pp. 456-469.

Bibtex

@article{74aadec4adf54adb954eaaa7ccdc9228,
title = "Globally flexible functional forms: the neural distance function",
abstract = "The output distance function is a key concept in economics. However, its empirical estimation often violates properties dictated by neoclassical production theory. In this paper, we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification. The NDF imposes all theoretical properties such as monotonicity, curvature and homogeneity, for all economically admissible values of outputs and inputs. Fitted to a large data set for all US commercial banks (1989–2000), the NDF explains a very high proportion of the variance of output while keeping the number of parameters to a minimum and satisfying the relevant theoretical properties. All measures such as total factor productivity (TFP) and technical efficiency (TE) are computed routinely. Next, the NDF is compared with the Translog popular specification and is found to provide very satisfactory results as it possesses the properties thought as desirable in neoclassical production theory in a way not matched by its competing specification.",
keywords = "Output distance function , Translog , Technical efficiency , ANN , LIML",
author = "Michaelides, {Panayotis G.} and Vouldis, {Angelos T.} and Michael Tsionas",
year = "2010",
month = oct,
doi = "10.1016/j.ejor.2010.02.013",
language = "English",
volume = "206",
pages = "456--469",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier Science B.V.",
number = "2",

}

RIS

TY - JOUR

T1 - Globally flexible functional forms

T2 - the neural distance function

AU - Michaelides, Panayotis G.

AU - Vouldis, Angelos T.

AU - Tsionas, Michael

PY - 2010/10

Y1 - 2010/10

N2 - The output distance function is a key concept in economics. However, its empirical estimation often violates properties dictated by neoclassical production theory. In this paper, we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification. The NDF imposes all theoretical properties such as monotonicity, curvature and homogeneity, for all economically admissible values of outputs and inputs. Fitted to a large data set for all US commercial banks (1989–2000), the NDF explains a very high proportion of the variance of output while keeping the number of parameters to a minimum and satisfying the relevant theoretical properties. All measures such as total factor productivity (TFP) and technical efficiency (TE) are computed routinely. Next, the NDF is compared with the Translog popular specification and is found to provide very satisfactory results as it possesses the properties thought as desirable in neoclassical production theory in a way not matched by its competing specification.

AB - The output distance function is a key concept in economics. However, its empirical estimation often violates properties dictated by neoclassical production theory. In this paper, we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification. The NDF imposes all theoretical properties such as monotonicity, curvature and homogeneity, for all economically admissible values of outputs and inputs. Fitted to a large data set for all US commercial banks (1989–2000), the NDF explains a very high proportion of the variance of output while keeping the number of parameters to a minimum and satisfying the relevant theoretical properties. All measures such as total factor productivity (TFP) and technical efficiency (TE) are computed routinely. Next, the NDF is compared with the Translog popular specification and is found to provide very satisfactory results as it possesses the properties thought as desirable in neoclassical production theory in a way not matched by its competing specification.

KW - Output distance function

KW - Translog

KW - Technical efficiency

KW - ANN

KW - LIML

U2 - 10.1016/j.ejor.2010.02.013

DO - 10.1016/j.ejor.2010.02.013

M3 - Journal article

VL - 206

SP - 456

EP - 469

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 2

ER -