This is a preview of subscription content, log in via an institution to check access.
Notes
“Survival of the citest” could be a more accurate word-play and catchphrase for academia.
The “elephant” distribution is one such entertaining example, see https://stats.stackexchange.com/a/283143.
For a comprehensive review of the wrong skewness problem in stochastic frontier analysis, see Papadopoulos and Parmeter (2023).
This study has been published as an MPRA working paper already in 2021, https://mpra.ub.uni-muenchen.de/110888/.
Papadopoulos and Parmeter (2023) discuss this matter in more detail.
Going back to our Darwinian take on pumping out new models and estimators, we mention that the authors include in their Appendix two additional models that do not suffer from said identification issue.
In relation to Table 2 of HPW2023 we must warn the reader that it is rather misleading to put in the same row the fixed “τ” from the AL-Exp model (first three columns of results), and the estimated quantile from the Corrected-Q model: the first three represent values for the zero-quantile of the noise component v. The latter is a value of the zero-quantile of the composed error ε = v − u. Essentially, the same symbol represents two different probabilities. So the AL-Exp column with value τ = Pr(v ≤ 0) = 0.8 is not comparable to the Corrected-Q column with value τ = Pr(ε ≤ 0) = 0.7953.
See Papadopoulos (2023) for a detailed exposition for this problem, and a wider exploration of the noise error component.
References
Badunenko O, Henderson DJ (2023) Production analysis with asymmetric noise. J Prod Anal. https://doi.org/10.1007/s11123-023-00680-5.
Bonanno G, De Giovanni D, Domma F (2017) The ‘wrong skewness’ problem: a re-specification of stochastic frontiers. J Prod Anal 47(1):49–64
Horrace WC, Parmeter CF, Wright IA (2023) On asymmetry and quantile estimation of the stochastic frontier model. J Prod Anal. https://doi.org/10.1007/s11123-023-00673-4.
Komunjer I (2005) Quasi-maximum likelihood estimation for conditional quantiles. J Econom 128(1):137–164
Lai Hp, Kumbhakar SC (2023) Indirect inference estimation of stochastic production frontier models with skew-normal noise. Empir Econom. https://doi.org/10.1007/s00181-023-02412-y.
Papadopoulos A (2015) The Half Normal specification for the two-tier stochastic frontier model. J Prod Anal 43(2):225–230
Papadopoulos A (2021) Measuring the effect of management on production: a two-tier stochastic frontier approach. Empir Econom 60:3011–3041
Papadopoulos A (2023) The noise error component in stochastic frontier analysis. Empir Econom 64:2795–2829
Papadopoulos A, Parmeter CF (2022) Quantile methods for stochastic frontier analysis. Found Trend Econom 12(1):1–120
Papadopoulos A, Parmeter CF (2023) The wrong skewness problem in stochastic frontier analysis: A review. J Prod Anal Forthcoming
Tsionas MG (2020) Quantile stochastic frontiers. Eur J Op Res 282(3):1177–1184
Wei Z, Zhu X, Wang T (2021) The extended skew-normal-based stochastic frontier model with a solution to “wrong skewness” problem. Statistics 55(6):1387–1406
Zhu X, Wei Z, Wang T (2022) Multivariate skew normal-based stochastic frontier models. J Stat Theor Pract 16(2):1–21
Author contributions
Being the sole author, I did everything.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Papadopoulos, A. Some notes on the asymmetry of the regression error. J Prod Anal 61, 37–42 (2024). https://doi.org/10.1007/s11123-023-00705-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11123-023-00705-z