Assessing Agricultural Support Policy Impact through Traditional versus Machine-Learning Techniques

Titolo Rivista Economia agro-alimentare
Autori/Curatori Orjon Xhoxhi, Engjell Skreli, Edvin Zhllima, Drini Imami
Anno di pubblicazione 2026 Fascicolo 2025/3
Lingua Inglese Numero pagine 20 P. 363-382 Dimensione file 0 KB
DOI 10.3280/ecag2025oa19419
Il DOI è il codice a barre della proprietà intellettuale: per saperne di più clicca qui

Vedi l'articolo Scarica l'articolo open access

FrancoAngeli è membro della Publishers International Linking Association, Inc (PILA)associazione indipendente e non profit per facilitare (attraverso i servizi tecnologici implementati da CrossRef.org) l’accesso degli studiosi ai contenuti digitali nelle pubblicazioni professionali e scientifiche

This paper analyses the impact of agricultural subsidies using traditional quasi-experimental research design that combines genetic matching procedure with regression analysis and causal forests, an adaptation of the random forest algorithm of Breiman (2001) for treatment effect estimation. The study is based on a structured orchard farm survey conducted in Albania, an EU candidate country. By employing both traditional and machine learning methods, the comparative methodological approach represents a notable contribution by enhancing the robustness of the findings, while highlighting the advantages of the random forest algorithm. The research results indicate that policy support significantly increased on-farm investments by approximately 4.7 million ALL (representing a 39% increase relative to the sample average investment for the analysed period), and direct apple revenues by about 2.48 million ALL (a 29% increase relative to the sample average revenue). Moreover, the policy had a substantial impact on altering the variety cultivation structure - beneficiary farmers replaced lower-quality apple varieties with higher-quality, market-demanded varieties, while non-beneficiaries showed no significant changes in their variety structure. As a result, the policy support enabled beneficiary farmers to better align their production structure with market demand, potentially boosting their future competitiveness.

Parole chiave:Agricultural subsidies;Impact assessment;Generalized Random Forest;Quasi-experimental;Albania

  1. AGT-DSA (2021). Fruit and vegetable sector study report, -- available at: <a href="https://ipard.gov.al/wp-content/uploads/2021/03/07-Fruit-Vegetable-Report__FINAL.pdf">https://ipard.gov.al/wp-content/uploads/2021/03/07-Fruit-Vegetable-Report__FINAL.pdf</a>.
  2. Athey, S., & Wager, S. (2019). Estimating treatment effects with causal forests: An application. Observational Studies, 5(1), 37-51.
  3. Athey, S., Tibshirani, J., & Wager, S. (2019). Generalized random forests. Ann. Statist., 47(2) 1148-1178. Doi: 10.1214/18-AOS1709.
  4. Bartolini, F., & Viaggi, D. (2013). The common agricultural policy and the determinants of changes in EU farm size. Land Use Policy, 31, 126-135. Doi: 10.1016/j.landusepol.2011.10.007.
  5. Bojnec, Š., & Fertő, I. (2019). Do CAP subsidies stabilise farm income in Hungary and Slovenia. Agricultural Economics (Agricecon), 65(3), 103-111.
  6. Bojnec, Š., & Fertő, I. (2022). Do different types of Common Agricultural Policy subsidies promote farm employment?. Land Use Policy, 112, 105823. Doi: 10.1016/j.landusepol.2021.105823.
  7. Breiman L. (2001). Random forests. Machine learning, 45(1), 5-32.
  8. Ciaian, P., Kancs, D. A., & Paloma, S. G. Y. (2015). Income distributional effects of CAP subsidies: micro evidence from the EU. Outlook on Agriculture, 44(1), 19-28. Doi: 10.5367/oa.2015.0196.
  9. Colen, L., Gomez y Paloma, S., Latacz‐Lohmann, U., Lefebvre, M., Préget, R., & Thoyer, S. (2016). Economic experiments as a tool for agricultural policy evaluation: insights from the European CAP. Canadian Journal of Agricultural Economics/Revue canadienne d’agroeconomie, 64(4), 667-694. Doi: 10.1111/cjag.12107.
  10. Diamond, A., & Sekhon, J. S. (2013). Genetic matching for estimating causal effects: A general multivariate matching method for achieving balance in observational studies. Review of Economics and Statistics, 95(3), 932-945. Doi: 10.1162/REST_a_00318.
  11. DiPrete, T. A., & Gangl, M. (2004). Assessing bias in the estimation of causal effects: Rosenbaum bounds on matching estimators and instrumental variables estimation with imperfect instruments. Sociological Methodology, 34(1), 271-310. Doi: 10.1111/j.0081-1750.2004.00154.x.
  12. Ertefaie, A., Small, D. S., & Rosenbaum, P. R. (2018). Quantitative evaluation of the trade-off of strengthened instruments and sample size in observational studies. Journal of the American Statistical Association, 113(523), 1122-1134. Doi: 10.1080/01621459.2017.1305275.
  13. FAO (2021). The state of the world’s plant genetic resources for food and agriculture, -- available at: <a href="https://openknowledge.fao.org/server/api/core/bitstreams/0172f037-db3b-47e8-9f93-26a1701db513/content">https://openknowledge.fao.org/server/api/core/bitstreams/0172f037-db3b-47e8-9f93-26a1701db513/content</a>.
  14. Gallerani, V., Gomez y Paloma, S., Raggi, M., & Viaggi, D. (2008). Modelling the effect of EU policy reforms on farm investment behaviour. In: Proceeding of 107th EAAE Seminar: Modelling Agricultural and Rural Development Policies, s.l, s.n, 2008, pp. 1-8 (atti di: 107th EAAE Seminar: Modelling Agricultural and Rural Development Policies, Siviglia, 29 gennaio - 1 febbraio 2008). Doi: 10.22004/ag.econ.6444.
  15. Gecaj, M., Shahu (Ozuni), E., Imami, D., Skreli, E., & Jambor, A. (2019). Analysing the impact of subsidies on the Albanian agriculture sector. Bulgarian Journal of Agricultural Science, 25(5), 883-890.
  16. Gerdoci, B., Skreli, E., & Imami, D. (2015). Relational governance – an examination of the apple sector in Albania. Journal of Central European Agriculture, 16(2), 0-0. Doi: 10.5513/JCEA01/16.2.1592.
  17. Hammel, K., & Arnold, T. (2012). Understanding the loss of traditional agricultural systems: A case study of orchard meadows in Germany. Journal of Agriculture, Food Systems, and Community Development, 2(4), 119-136. Doi: 10.5304/jafscd.2012.024.011.
  18. Imbens G. W., & Rubin D. B. (2015). Causal inference in statistics, social, and biomedical sciences. USA, Cambridge University Press.
  19. King, G., & Nielsen, R. (2019). Why propensity scores should not be used for matching. Political Analysis, 27(4), 435-454.
  20. Kirchweger, S., Kantelhardt, J., & Leisch, F. (2015). Impacts of the government supported investments on the economic farm performance in Austria. Agricultural Economics, 61(8), 343-355.
  21. Latruffe, L., & Desjeux, Y. (2016). Common agricultural policy support, technical efficiency, and productivity change in french agriculture. Review of Agricultural, Food and Environmental Studies, 97(1), 15-28.
  22. Latruffe, L., Bravo - Ureta, B. E., Carpentier, A., Desjeux, Y. and Moreira, V. H. (2017). Subsidies and technical efficiency in agriculture: Evidence from European dairy farms. American Journal of Agricultural Economics, 99(3), 783-799. Doi: 10.1093/ajae/aaw077.
  23. Lien, G., Kumbhakar, S. C., & Hardaker, J. B. (2010). Determinants of off‐farm work and its effects on farm performance: the case of Norwegian grain farmers. Agricultural Economics, 41(6), 577-586. Doi: 10.1111/j.1574-0862.2010.00473.x.
  24. Minviel, J. J., & Latruffe, L. (2017). Effect of public subsidies on farm technical efficiency: a meta-analysis of empirical results. Applied Economics, 49(2), 213-226. Doi: 10.1080/00036846.2016.1194963.
  25. O’Toole, C., & Hennessy, T. (2015). Do decoupled payments affect investment financing constraints? Evidence from Irish agriculture. Food Policy, 56, 67-75. Doi: 10.1016/j.foodpol.2015.07.004.
  26. OECD (2024). Agricultural policy monitoring and evaluation 2024: Innovation for Sustainable Productivity Growth. OECD Publishing, Paris. Doi: 10.1787/74da57ed-en.
  27. Olper, A., Raimondi, V., Vigani, M., & Cavicchioli, D. (2012). Does the common agricultural policy reduce farm labour migration? Panel data analysis across EU regions.
  28. Petrick, M., & Zier, P. (2012). Common Agricultural Policy effects on dynamic labour use in agriculture. Food policy, 37(6), 671-678. Doi: 10.1016/j.foodpol.2012.07.004.
  29. Powell, J. R., Vigani, M., Hawketts, E., Schuh, B., Gorny, H., Kaucic, J., & Kirchmayr-Novak, S. (2016). The role of the EU’s Common Agricultural Policy in creating rural jobs.
  30. Reise, C., Musshoff, O., Granoszewski, K., & Spiller, A. (2012). Which factors influence the expansion of bioenergy? An empirical study of the investment behaviours of German farmers. Ecological Economics, 73, 133-141. Doi: 10.1016/j.ecolecon.2011.10.008.
  31. Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41-55. Doi: 10.1093/biomet/70.1.41.
  32. Rosenbaum, P. R., & Rubin, D. B. (1985). Constructing a control group using multivariate matched sampling methods that incorporate the propensity score. The American Statistician, 39(1), 33-38.
  33. Scornet, E., Biau, G., & Vert, J. P. (2015). Consistency of Random Forests. Annals of Statistics, 43(4), 1716-1741.
  34. Skreli, E., Imami, D., Jámbor, A., Zvyagintsev, D., & Cera, G. (2015). The impact of government subsidies on the olive and vineyard sectors of Albanian agriculture. Studies in Agricultural Economics, 117(3), 119-125. Doi: 10.22004/ag.econ.231516.
  35. Skreli, E., Xhoxhi, O., Zhllima, E., & Imami, D. (2024). Do Agriculture Subsidies Make Farmers Better-off? A Case Study from an EU Candidate Country. Studies in Agricultural Economics, 126(3). Doi: 10.7896/j.2885.
  36. Skreli, E., & Imami, D. (2019). MAPs sector study. Technical report prepared for EBRD, -- available at: <a href="https://aatsf.com.al/wp-content/uploads/2020/04/4Mapcover-EN.pdf">https://aatsf.com.al/wp-content/uploads/2020/04/4Mapcover-EN.pdf</a>.
  37. Stojcheska, A. M., Zhllima, E., Kotevska, A., & Imami, D. (2024). Western Balkans agriculture and rural development policy in the context of EU integration-The case of Albania and North Macedonia. Regional Science Policy & Practice, 16(8), 100049. Doi: 10.1016/j.rspp.2024.100049.
  38. Wager, S., & Athey, S. (2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228-1242.

Orjon Xhoxhi, Engjell Skreli, Edvin Zhllima, Drini Imami, Assessing Agricultural Support Policy Impact through Traditional versus Machine-Learning Techniques in "Economia agro-alimentare" 3/2025, pp 363-382, DOI: 10.3280/ecag2025oa19419