To read the full version of this content please select one of the options below:

Conventional procedure vis-à-vis bootstrap-based corrections of efficiency analyses

Vipin Valiyattoor (Department of Humanities and Social Sciences, Indian Institute of Technology Madras, Chennai, India)
Anup Kumar Bhandari (Department of Humanities and Social Sciences, Indian Institute of Technology Madras, Chennai, India)

Indian Growth and Development Review

ISSN: 1753-8254

Article publication date: 3 February 2020

Issue publication date: 15 December 2020

Abstract

Purpose

This paper aims to evaluate the performance of basic metals industry in India and analyze its determinants, using data envelopment analysis (DEA) method. It also intends to compare the results through conventional two-stage and bootstrap-based inferences.

Design/methodology/approach

Considering technical efficiency as a measure of performance, this paper specifically investigates whether the participation of a firm in the global market affects its performance. The conventional two-stage procedure is used to test the export intensity and firm performance nexus. The bootstrap-based algorithms (by Simar and Wilson, 2007) are used to correct the bias and serial correlation issues involved in the conventional approach.

Findings

The result shows a negative relation between export intensity and firm performance while following the conventional procedure. Even after accounting for serial correlation, the relation remains more or less similar to that of conventional analysis. However, a strong negative relation between export intensity and firm performance is not observed in a more reliable inference obtained after correcting for possible bias as well as serial correlation.

Research limitations/implications

This paper is based on cross-sectional analysis, and a more reliable result can be obtained by considering a larger sample and longer period.

Originality/value

This paper shows how the conventional two-stage procedure may result in misleading inferences due to bias in the estimation of efficiency scores and the serial correlation during the second stage inferential analysis. This paper also empirically exemplifies how the double bootstrap DEA procedure can overcome these limitations of the conventional two-stage approach.

Keywords

Acknowledgements

Compliance with Ethical Standards: No potential conflict of interest was reported by the author.

Ethical approval: This article does not contain any studies with human participants or animals performed by the author.

Funding Information: The author (s) received no specific funding for this work.

Citation

Valiyattoor, V. and Bhandari, A.K. (2020), "Conventional procedure vis-à-vis bootstrap-based corrections of efficiency analyses", Indian Growth and Development Review, Vol. 13 No. 3, pp. 505-536. https://doi.org/10.1108/IGDR-04-2019-0035

Publisher

:

Emerald Publishing Limited

Copyright © 2020, Emerald Publishing Limited