# References

## What published references underpin the methodology? {#what-published-references-underpin-the-methodology}

The methodology rests on an established body of reference literature — textbooks, statistical manuals, and technical papers spanning the economics of commodity markets and the robust-statistics techniques used to estimate prices from trade data. This shared foundation was drawn on throughout the development of the methodology and the elaboration of its models, so that any reader can trace the underlying concepts and techniques to their primary sources.

{.compact}
| No. | Reference |
| --- | --- |
| 1 | Atkinson, A. C. et al. 2017. Robust Bayesian Regression with the Forward Search: Theory and Data Analysis. Test, vol. 26, pp. 869–886. |
| 2 | International Energy Agency. 2004. Energy Statistics Manual. IEA, Paris. |
| 3 | International Monetary Fund. 2009. Balance of Payments and International Investment Position Manual (6th ed.). |
| 4 | International Monetary Fund. 2009. Export and Import Price Index Manual. Organisation for Economic Co-operation and Development. |
| 5 | Mankiw, G. 2020. Principles of Economics (9th ed.). Cengage. |
| 6 | Miao, G.; Wegner, E. 2022. Using Unit Value Indices as Proxies for International Merchandise Trade Prices. SDD Working Paper No. 111. Organisation for Economic Co-operation and Development, Paris. |
| 7 | Perrotta, D. et al. 2020. The Robust Estimation of Monthly Prices of Goods Traded by the European Union. EUR 30188 EN. Publications Office of the European Union, Luxembourg. ISBN 978-92-76-18351-8. doi:10.2760/635844. |
| 8 | Riani, M. et al. 2018. The Use of Prior Information in Very Robust Regression for Fraud Detection. International Statistical Review, vol. 86(2), pp. 205–218. |
| 9 | Rais, S. 2008. Outlier Detection for the Consumer Price Index. In Proceedings of the Survey Methods Section: Statistical Society of Canada Annual Meeting, vol. 110. |
| 10 | Schofield, N. C. 2021. Commodity Derivatives: Markets and Applications (2nd ed.). John Wiley and Sons. |
| 11 | Spyros, A. et al. 2015. The Estimation of Fair Prices of Traded Goods from Outlier-free Trade Data. EUR 27696 EN. doi:10.2788/57125. |
| 12 | Temere, Dawit Sisay. 2016. Disaggregated International Trade Prices. Nationaløkonomisk Tidsskrift. |
| 13 | United Nations. 1981. Strategies for Price and Quantity Measurement in External Trade: A Technical Report. Series M, No. 69. |
| 14 | United Nations. 2018. International Recommendations for Energy Statistics. Series M, No. 93. |

## How does Intratec keep its reference sources independent? {#how-does-intratec-keep-its-reference-sources-independent}

Every work in this list is a published, independently obtainable source — a textbook, an official statistical manual, or a peer-reviewed technical paper — rather than a proprietary or vendor-supplied dataset. Anyone can obtain the original and check it, so the foundations of the methodology can be audited without relying on Intratec's own account of them. The statistical techniques are drawn from the open literature on robust estimation, and any external index consulted while calibrating a model serves only as an internal reference point — it is never republished or presented as a source. This mirrors the data-side commitments described in [What independence commitments back the analysis?](../independence-and-limitations/independence.md#what-independence-commitments-back-the-analysis): impartial, publicly grounded inputs at every layer.

## When is a new source added to this reference list? {#when-is-a-new-source-added-to-this-reference-list}

A reference is added when a change to the methodology introduces a technique, data treatment, or convention that a published work underpins — adopting a new robust-estimation method or a revised trade-statistics standard, for instance. A source is likewise removed or replaced when the technique it supported is retired. The list therefore tracks the methods actually in use rather than the wider literature on the subject. The schedule on which such changes are reviewed and released is described in [How often is the methodology reviewed?](../validation-and-accuracy/accuracy-improvement.md#how-often-is-the-methodology-reviewed).

## Where are the recurring methodology terms defined? {#where-are-the-recurring-methodology-terms-defined}

Recurring terms used throughout the methodology — the price types, the data status labels (Final, Preliminary, and Forecast), the accuracy metrics (mean absolute percentage error, mean absolute percentage accuracy, directional accuracy, and the model performance score), and the pricing conventions (netback, netforward, and the Incoterms that fix each assessment basis) — are defined in full in the [Glossary](../glossary/glossary.md). Reading the Glossary alongside any article keeps the meaning of a term identical across every part of the methodology, so a definition never has to be repeated or paraphrased inside an individual answer.

## Where can the up-to-date methodology be found? {#where-can-the-up-to-date-methodology-be-found}

The complete methodology is published in full on this methodology site, where it is continuously updated as models and data sources evolve. It requires no subscription and no login: every step, from raw inputs to a finished assessment, is openly available to read. Changes to the methodology and to the underlying data are documented as they are made, so the version on the site is always the current one — there is no separate edition to request or purchase.