MARC

Tag First Indicator Second Indicator Subfields
LEADER 00000cam a2200000Ii 4500
001 in00001482921
005 20191026063207.0
008 990503e198905 txua bt s000 0 eng d
035 |a (OCoLC)ocm41289686 
035 |9 AJG4062AM 
040 |a TXA  |b eng  |e rda  |c TXA  |d OCLCQ  |d OCLCF  |d OCLCO  |d UMI  |d TXA 
035 |a (OCoLC)41289686 
090 |a QA276.A12  |b T4 no.55 
049 |a TXAM 
100 1 |a Grimshaw, Scott D.,  |d 1962-  |e author. 
245 1 2 |a A unified approach to estimating tail behavior /  |c Scott D. Grimshaw. 
264 1 |a College Station, Texas :  |b Department of Statistics, Texas A & M University,  |c 1989. 
300 |a 107 pages :  |b illustrations ;  |c 28 cm 
336 |a text  |b txt  |2 rdacontent 
337 |a unmediated  |b n  |2 rdamedia 
338 |a volume  |b nc  |2 rdacarrier 
490 1 |a Technical report ;  |v no. 55 
500 |a "May 1989." 
500 |a "Texas A & M Research Foundation, Project No. 5641." 
504 |a Includes bibliographical references (pages 81-84). 
513 |a Technical report. 
520 3 |a Tail estimators are proposed which make minimal assumptions and let the data dictate the form of the probability model. These estimators use only the observations in the tail and are based on a unifying density-quantile model. The fundamental result in this work is a representation of the quantile function of the exceedences over a threshold. This representation (1) motivates a unified parameterization for tail estimators of the underlying probability model; (2) motivates methods for obtaining parameter estimates; and (3) simplifies the derivation of the asymptotic properties of the proposed parameter estimates. Parameter estimates may be obtained using a Generalized Pareto Distribution or a Generalized Extreme Value Distribution model of the exceedences. Assuming the underlying distribution can be correctly classified as either short tailed or long tailed, other estimates are formed. The asymptotic properties of these estimates are derived under rate of convergence conditions to show the effect of threshold selection on parameter properties. The parameters are shown to be nonidentifiable and their estimators contain a bias which may approach zero very slowly. Therefore, if the parameters are the focus of the analysis, extremely large sample sizes are required to reduce the bias to a negligible amount. If the tail estimates are of interest, the bias is less likely to be serious and the nonidentifiability problem provides a closer approximation to the tail for small samples. 
536 |a Sponsored by the U.S. Army Research Office  |b DAAL03-87-K-0003 
650 0 |a Extreme value theory. 
650 0 |a Estimation theory  |x Asymptotic theory. 
650 0 |a Parameter estimation. 
650 0 |a Convergence. 
650 0 |a Regression analysis. 
650 0 |a Mathematical statistics. 
650 7 |a Statistics  |x Nonparametric inference  |x Statistics of extreme values; tail inference.  |2 msc 
650 7 |a Regression analysis.  |2 fast  |0 (OCoLC)fst01432090 
650 7 |a Statistics.  |2 fast  |0 (OCoLC)fst01132103 
653 0 |a Quantile data analysis 
653 0 |a Extreme value distributions 
653 0 |a Pareto distributions 
653 0 |a Tail estimation 
653 0 |a Exceedances over threshold 
710 2 |a Texas A & M University.  |b Department of Statistics,  |e issuing body. 
710 1 |a United States.  |b Army Research Office,  |e sponsoring body. 
710 2 |a Texas A & M Research Foundation. 
775 0 8 |i Revision of:  |a Grimshaw, Scott D., 1962-  |t Unified approach to estimating tail behavior.  |d 1989  |w (OCoLC)20940934 
830 0 |a Technical report (Texas A & M University. Department of Statistics) ;  |v no. 55. 
948 |a cataloged  |b h  |c 2018/04/06  |d o  |e zdobbs  |f 4:25:19 pm 
948 |a o:br 
994 |a C0  |b TXA 
999 f f |s 88bce063-bae6-3178-ad08-962a310cbb6d  |i 24b6461b-addd-3e9b-b028-b8019690d9f1  |t 0 
952 f f |p noncirc  |a Texas A&M University  |b College Station  |c Cushing Memorial Library & Archives  |d Cushing: Texas A&M Publications (Remote Storage: 2-3 day retrieval)  |t 0  |e QA276.A12 T4 no.55  |h Library of Congress classification  |i unmediated -- volume 
998 f f |a QA276.A12 T4 no.55  |t 0  |l Cushing: Texas A&M Publications (Remote Storage: 2-3 day retrieval)