DEA-Inspired Constrained Log-Log Quantile Frontier: Smooth Bench-marking, Calibration, and Dynamic Interpretation; Contemporary Mathematics; Vol. 7, iss. 3

Bibliografiset tiedot
Parent link:Contemporary Mathematics.— .— Singapore: Universal Wiser Publisher
Vol. 7, iss. 3.— 2026.— 32 p.
Muut tekijät: Spitsin V. V. Vladislav Vladimirovich, Martyushev N. V. Nikita Vladimirovich, Spitsina (Spitsyna) L. Yu. Lubov Yurievna, Gasanov M. A. Magerram Ali Ogly, Leonova V. A. Victoria Aleksandrovna
Yhteenveto:Title screen
This paper proposes a Data Envelopment Analysis (DEA)-inspired smooth benchmarking approach based ona constrained log-log quantile production frontier. The frontier is estimated by quantile regression under economicallymotivated inequality restrictions—monotonicity in inputs and a non-increasing-returns (concavity-compatible) restrictionwithin the Cobb-Douglas class—yielding a continuously differentiable benchmark with elasticity-based interpretationand tractable inference via constrained quantile regression theory. Our contribution is threefold: we (i) formalize large-sample inference for constrained quantile frontiers under economically interpretable inequality restrictions, (ii) introducea calibration perspective for probabilistic frontiers via exceedance/coverage diagnostics (and a simple non-crossingadjustment for multiple quantiles), and (iii) derive closed-form links between output- and input-oriented quantile efficiencyindices through the returns-to-scale parameter, together with a high-quantile interpretation within a one-sided stochasticproduction model. We emphasize the probabilistic nature of quantile frontiers: for any fixed quantile levelτ∈(0,1),the fitted frontier is a coverage benchmark rather than a deterministic envelopment surface, so a non-negligible share ofobservations may lie above it. Empirically, we apply the framework to firm-level panel data from the SPARK-Interfaxinformation system covering 1,035 Russian manufacturing firms over 2019–2023 (5,175 firm-year observations). Webenchmark the proposed smooth quantile frontier against classical DEA and a parametric Stochastic Frontier Analysis(SFA), and we report internal validation (pinball loss, coverage) together with sensitivity diagnostics acrossτ. The resultingefficiency measures exhibit significant associations with profitability (net Return onAssets (ROA)), changes in profitability,and sales growth, indicating economic relevance. Overall, the proposed approach complements deterministic envelopmentby providing smooth differentiability, robustness to noise, and calibration-driven interpretability for heterogeneous datasets,while retaining economically meaningful shape discipline and enabling a dynamic decomposition of frontier shifts andrelative performance
Текстовый файл
AM_Agreement
Kieli:englanti
Julkaistu: 2026
Aiheet:
Linkit:https://doi.org/10.37256/cm.7320269045
Aineistotyyppi: Elektroninen Kirjan osa
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=686426

MARC

LEADER 00000naa0a2200000 4500
001 686426
005 20260507094621.0
090 |a 686426 
100 |a 20260507d2026 k||y0rusy50 ba 
101 0 |a eng 
102 |a SG 
135 |a drcn ---uucaa 
181 0 |a i   |b  e  
182 0 |a b 
183 0 |a cr  |2 RDAcarrier 
200 1 |a DEA-Inspired Constrained Log-Log Quantile Frontier: Smooth Bench-marking, Calibration, and Dynamic Interpretation  |f Vladislav Spitsin, Nikita Martyushev, Lubov Spitsina [et al.] 
203 |a Текст  |b визуальный  |c электронный 
283 |a online_resource  |2 RDAcarrier 
300 |a Title screen 
320 |a References: 37 tit 
330 |a This paper proposes a Data Envelopment Analysis (DEA)-inspired smooth benchmarking approach based ona constrained log-log quantile production frontier. The frontier is estimated by quantile regression under economicallymotivated inequality restrictions—monotonicity in inputs and a non-increasing-returns (concavity-compatible) restrictionwithin the Cobb-Douglas class—yielding a continuously differentiable benchmark with elasticity-based interpretationand tractable inference via constrained quantile regression theory. Our contribution is threefold: we (i) formalize large-sample inference for constrained quantile frontiers under economically interpretable inequality restrictions, (ii) introducea calibration perspective for probabilistic frontiers via exceedance/coverage diagnostics (and a simple non-crossingadjustment for multiple quantiles), and (iii) derive closed-form links between output- and input-oriented quantile efficiencyindices through the returns-to-scale parameter, together with a high-quantile interpretation within a one-sided stochasticproduction model. We emphasize the probabilistic nature of quantile frontiers: for any fixed quantile levelτ∈(0,1),the fitted frontier is a coverage benchmark rather than a deterministic envelopment surface, so a non-negligible share ofobservations may lie above it. Empirically, we apply the framework to firm-level panel data from the SPARK-Interfaxinformation system covering 1,035 Russian manufacturing firms over 2019–2023 (5,175 firm-year observations). Webenchmark the proposed smooth quantile frontier against classical DEA and a parametric Stochastic Frontier Analysis(SFA), and we report internal validation (pinball loss, coverage) together with sensitivity diagnostics acrossτ. The resultingefficiency measures exhibit significant associations with profitability (net Return onAssets (ROA)), changes in profitability,and sales growth, indicating economic relevance. Overall, the proposed approach complements deterministic envelopmentby providing smooth differentiability, robustness to noise, and calibration-driven interpretability for heterogeneous datasets,while retaining economically meaningful shape discipline and enabling a dynamic decomposition of frontier shifts andrelative performance 
336 |a Текстовый файл 
371 0 |a AM_Agreement 
461 1 |t Contemporary Mathematics  |c Singapore  |n Universal Wiser Publisher 
463 1 |t Vol. 7, iss. 3  |v 32 p.  |d 2026 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a constrained quantile regression 
610 1 |a log-log quantile frontier 
610 1 |a Data Envelopment Analysis (DEA) benchmarking 
610 1 |a shape restrictions 
610 1 |a calibration 
610 1 |a non-crossing quantiles 
610 1 |a technical efficiency 
610 1 |a dynamic decomposition 
701 1 |a Spitsin  |b V. V.  |c economist  |c Associate Professor of Tomsk Polytechnic University, Candidate of economic sciences  |f 1976-  |g Vladislav Vladimirovich  |9 15195 
701 1 |a Martyushev  |b N. V.  |c specialist in the field of material science  |c Associate Professor of Tomsk Polytechnic University, Candidate of technical sciences  |f 1981-  |g Nikita Vladimirovich  |9 16754 
701 1 |a Spitsina (Spitsyna)  |b L. Yu.  |c Economist  |c Associate Professor of Tomsk Polytechnic University, Candidate of economic sciences  |f 1976-  |g Lubov Yurievna  |9 18510 
701 1 |a Gasanov  |b M. A.  |c Economist  |c Professor of Tomsk Polytechnic University, Doctor of economic sciences (DSc)   |f 1963-  |g Magerram Ali Ogly  |9 17176 
701 1 |a Leonova  |b V. A.  |c specialist in the field of economics  |c assistant of Tomsk Polytechnic University  |f 1998-  |g Victoria Aleksandrovna  |9 88586 
801 0 |a RU  |b 63413507  |c 20260507 
850 |a 63413507 
856 4 0 |u https://doi.org/10.37256/cm.7320269045  |z https://doi.org/10.37256/cm.7320269045 
942 |c CF