Inference about the Tail of a Distribution: Improvementon the Hill Estimator

<table>A <svg height="17.125" id="M395" style="vertical-align:-2.457pt" version="1.1" viewbox="0 0 37.775002 17.125" width="37.775002" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,15.225,12.862)"><path d="M782 703l-309 -950l-231 505l-91 -47l-18 35l147 78l194 -431h2l264 810h42z" id="x221A"></path></g><g transform="matrix(.017,-0,0,-.017,.062,14)"><path d="M384 0h-275v27q67 5 81.5 18.5t14.5 68.5v385q0 38 -7.5 47.5t-40.5 10.5l-48 2v24q85 15 178 52v-521q0 -55 14.5 -68.5t82.5 -18.5v-27z" id="x31"></path></g><g transform="matrix(.017,-0,0,-.017,8.222,14)"><path d="M368 703l-264 -866h-60l265 866h59z" id="x2F"></path></g>
<g transform="matrix(1.25,0,0,-1.25,90,90)">
<path d="m -49.43,70.93 7.6,0" style="fill:none;stroke:#000000;stroke-width:0.68000001;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:10;stroke-opacity:1;stroke-dasharray:none"></path>
</g>
<g transform="matrix(.017,-0,0,-.017,28.212,14)"><path d="M536 404q0 -17 -13.5 -31.5t-26.5 -14.5q-8 0 -15 10q-11 14 -25 14q-22 0 -67 -50q-47 -52 -68 -82l37 -102q31 -88 55 -88t78 59l16 -23q-32 -48 -68.5 -78t-65.5 -30q-19 0 -37.5 20t-29.5 53l-41 116q-72 -106 -114.5 -147.5t-79.5 -41.5q-21 0 -34.5 14t-13.5 37
q0 16 13.5 31.5t28.5 15.5q12 0 17 -11q5 -10 25 -10q22 0 57.5 36t89.5 111l-40 108q-22 58 -36 58q-21 0 -67 -57l-19 20q81 107 125 107q17 0 30 -22t39 -88l22 -55q68 92 108.5 128.5t74.5 36.5q20 0 32.5 -14t12.5 -30z" id="x1D465"></path></g>
</svg> behavior (see Example<svg height="11.125" id="M396" style="vertical-align:-0.1638pt" version="1.1" viewbox="0 0 22.112499 11.125" width="22.112499" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,5.725,10.862)"><path d="M384 0h-275v27q67 5 81.5 18.5t14.5 68.5v385q0 38 -7.5 47.5t-40.5 10.5l-48 2v24q85 15 178 52v-521q0 -55 14.5 -68.5t82.5 -18.5v-27z" id="x31"></path></g><g transform="matrix(.017,-0,0,-.017,13.884,10.862)"><path d="M447 623l8 -12l-283 -613l-74 -10l-7 11q174 283 297 551h-216q-48 0 -62.5 -12t-33.5 -63h-29q10 60 18 148h382z" id="x37"></path></g>
</svg>).</table>

International Journal of Mathematics and Mathematical Sciences

fig4

Figure 4

Figure 4: Inference about the Tail of a Distribution: Improvementon the Hill Estimator 