Heavy tail probability distributions are important in many scientific disciplines such as hydrology, geology, and physics and therefore feature heavily in statistical practice. Rather than specifying a family of heavy-tailed distributions for a given application, it is more common to use a nonparametric approach, where the distributions are classified according to the tail behavior. Through the use of the logarithm of Parzen’s density-quantile function, this work proposes a consistent, flexible estimator of the tail exponent. The approach we develop is based on a Fourier series estimator and allows for separate estimates of the left and right tail exponents. The theoretical properties for the tail exponent estimator are determined, and we also provide some results of independent interest that may be used to establish weak convergence of stochastic processes. We assess the practical performance of the method by exploring its finite sample properties in simulation studies. The overall performance is competitive with classical tail index estimators, and, in contrast with these, our method obtains somewhat better results in the case of lighter heavy-tailed distributions.
CITATION: Holan, Scott and McElroy, Tucker. (2009). Tail Exponent Estimation via Broadband Log Density-Quantile Regression. Statistical Research Division Research Report Series (Statistics #2009-02). U.S. Census Bureau. Available online at <http://www.census.gov/srd/papers/pdf/rrs2009-02.pdf>.
Source: U.S. Census Bureau, Statistical Research Division
Published online: February 26, 2009
Last revised: February 24, 2009
This symbol indicates a link to a non-government web site. Our linking to these sites does not constitute an endorsement of any products, services or the information found on them. Once you link to another site you are subject to the policies of the new site.