By-Production Technology DEA
Data Envelopment Analysis with By-Product Treatment (By-Production Technology DEA) · Also known as: By-Production DEA, Joint Production DEA
By-Production Technology DEA is a variant of Data Envelopment Analysis designed for production systems that generate both desirable outputs and undesirable by-products or emissions. Rather than ignoring or arbitrarily penalizing undesirable outputs, this method explicitly models them as joint products of the production process. It evaluates efficiency while accounting for the trade-off between desired production and environmental impact.
Read the full method
Sign in with a free account to read this section.
Method map
The neighbourhood of related methods — select a node to explore.
When to use it
Use By-Production Technology DEA when evaluating organizations or processes that generate undesirable outputs inseparable from production. It is ideal for environmental management, pollution control assessment, and situations where regulations require accounting for emissions. Prefer it when by-products are inherent to production, not merely consequences of inefficiency.
Strengths & limitations
- Explicitly accounts for undesirable outputs; no artificial weighting or penalization needed
- Recognizes technology constraints; models the trade-off between good and bad outputs realistically
- Environmentally informed; suitable for sustainability assessment and environmental compliance
- Non-parametric; makes no assumptions about functional form of the production-pollution relationship
- Identifies best practices; shows efficient operations that balance production with environmental responsibility
- Requires classifying outputs as good or bad; ambiguous cases (e.g., is water pollution sometimes desirable?) complicate modeling
- Sensitive to by-product scaling; if bad outputs are measured in different units than good ones, normalization affects results
- Can produce dominated units; some units may be inefficient in both good and bad outputs, making comparison difficult
- Limited practical guidance; DEA identifies efficient frontier but may not suggest specific improvements
Frequently asked
How do I handle by-products that are only partially undesirable?
If a by-product has some value (e.g., waste heat for cogeneration), split it: treat the productive portion as a good output and the remaining waste as a bad output. Alternatively, model it with a directional efficiency approach.
What if regulations ban certain by-products entirely?
By-Production Technology DEA assumes by-products are unavoidable. If a by-product is banned, either it does not exist (units are in full compliance) or units are non-feasible. Adjust the model to classify such units separately.
Can I use this with many by-products (e.g., multiple pollutants)?
Yes, but curse of dimensionality applies. With many bad outputs, the sample size needed grows rapidly. Consider aggregating by-products into composite indices (e.g., CO2-equivalent emissions).
Sources
- Scheel, H. (2001). Undesirable outputs in efficiency valuations. European Journal of Operational Research, 132(2), 400-410. DOI: 10.1016/s0377-2217(00)00160-0 ↗
- Färe, R., Grosskopf, S., Noh, D. W., & Weber, W. (2005). Characteristics of a polluting technology: Theory and practice. Journal of Econometrics, 126(2), 469-492. DOI: 10.1016/j.jeconom.2004.05.010 ↗
How to cite this page
ScholarGate. (2026, June 3). Data Envelopment Analysis with By-Product Treatment (By-Production Technology DEA). ScholarGate. https://scholargate.app/en/decision-making/by-production-technology-dea
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- DEADecision-making↔ compare
- Network DEAEfficiency Analysis↔ compare