The Effect of Appeals on Assessment Ratio Distributions: Some Nonparametric Approaches

A variety of nonparametric methods-locally weighted regression, nonparametric quantile regression and conditional density functions-are used to evaluate the effect of appeals on assessment uniformity. Unlike previous studies, the focus is on the full distribution of assessment ratios rather than on central moments. Data for single-family homes in Chicago for 2006 suggest that appeals lead to a modest reduction in assessment variability, but the density of extremely high assessment ratios is higher among homes without appeals. Whereas traditional methods simply indicate that assessment ratios decline with sale price, nonparametric approaches reveal that higher prices have a more pronounced effect on the variance than on the conditional expectation of the assessment ratio distribution and that the most pronounced degree of regressivity occurs at very low sales prices.