Estimating tax noncompliance with evidence from unaudited tax returns

This article estimates the degree of tax noncompliance using evidence from unaudited tax returns. Measurements of noncompliance are derived from the relationship between reported charitable contributions and reported income from wages and salary as compared to alternative reported income sources such as self-employment, farm and other small business income. Assuming that the source of one's income is unrelated to one's charitable inclinations and that the ratio of true income to taxable income does not vary by income source, any difference in the relationship between charitable contributions and the source of income can be attributed to (relative) underreporting by the individual. We find that the implied amount of noncompliance is significant and that it varies by source of income, as well as between positive and negative values of each type of income. Copyright 2007 The Author(s). Journal compilation Royal Economic Society 2007.