The work was developed as part of the activities of the Task Force Monitoring & Evaluation of the National Rural Network. The publication deals with a particular methodology, the Statistical matching, for a counter-factual analysis. The work suggests a possible pathway for the formation of the control group, highlighting the role of the Farm Accountancy Data Network (FADN) for the evaluation of Rural Development Programmes.

The intent is to provide guidance, with respect to the most frequently used methodologies, and show the results of an experiment on the matching technique. Among the aid policies, the main strategies adopted in order to measure their impact, are based on the observation of the companies receiving the subsidy (before and after), or on the study of the differences between the group of companies that have benefited from grant and those which, however, were excluded.

Both methods generate misrepresentations in the estimates of impact (omitted variables bias, selection bias), nevertheless it is possible to adopt some methods which limit their range. The basic idea of the Matching is to combine each beneficiary with a not beneficiary, which is as similar as possible.

The matching is considered in literature a good method to compare treated and untreated, where the selection to treatment is completely determined by observable variables by the researcher and  subjected to a random assignment. 

[Read more]