Since 1998 Italy has adopted a method to audit small businesses (Studi di
Settore), which defines the probability of tax audits based on presumptive
and reported levels of output. In 2007 a letter campaign was implemented by
the Italian Tax Agency aimed at reducing manipulation of input reports for
tax purposes threatening that if the "anomaly" was not removed with the 2008
tax declaration, the probability of a thorough tax audit would have
drastically increased.
In this paper we analyze a large data set produced by the Tax Agency for
this project and made of about 50,000 treated firms and 150,000 controls
using Coarsened Exact Matching (CEM) methods to control ex-ante for
imbalance.
We find that the letter campaign had a positive and statistically
significant effect looking on the average treatment effect on the treated.
© 2025 | Università degli studi di Verona
******** CSS e script comuni siti DOL - frase 9957 ********
