Home | Contents | Submissions, editors, etc. | Login | Search | ECP
 Electronic Journal of Probability > Vol. 12 (2007) > Paper 47 open journal systems 


Uniformly Accurate Quantile Bounds Via The Truncated Moment Generating Function: The Symmetric Case

Michael J Klass, University of California Departments of Mathematics and Statistics Berkeley, CA
Krzysztof Nowicki, Lund University Department of Statistics Box 743 S-220 07 Lund, Sweden


Abstract
Let X1, X2,... be independent and symmetric random variables such that Sn=X1+...+Xn converges to a finite valued random variable S a.s. and let
S*=sup1 ≤ n<∞Sn
(which is finite a.s.). We construct upper and lower bounds for sy and sy*, the upper 1/y-th quantile of Sy and S*, respectively. Our approximations rely on an explicitly computable quantity qy for which we prove that
0.5 qy/2<sy*<2 q2y and 0.5 q0.25 y(1+√1-8/y) <sy <2 q2y.
The RHS's hold for y ≥2 and the LHS's for y ≥ 94 and y ≥97, respectively. Although our results are derived primarily for symmetric random variables, they apply to non-negative variates and extend to an absolute value of a sum of independent but otherwise arbitrary random variables.


Full text: PDF

Pages: 1276-1298

Published on: October 16, 2007


Bibliography
  1. H. Cramer, On a new limit in theory of probability, in Colloquium on the Theory of Probability, (1938), Hermann, Paris. Review number not available.
  2. F. Esscher, On the probability function in the collective theory of risk, Skand. Aktuarietidskr. 15 (1932), 175---195. Review number not available.
  3. Hahn, Marjorie G.; Klass, Michael J. Uniform local probability approximations: improvements on Berry-Esseen. Ann. Probab. 23 (1995), no. 1, 446--463. MR1330778 (96d:60069)
  4. Hahn, Marjorie G.; Klass, Michael J. Approximation of partial sums of arbitrary i.i.d. random variables and the precision of the usual exponential upper bound. Ann. Probab. 25 (1997), no. 3, 1451--1470. MR1457626 (99c:62039)
  5. Fuk, D. H.; Nagaev, S. V. Probabilistic inequalities for sums of independent random variables.(Russian) Teor. Verojatnost. i Primenen. 16 (1971), 660--675. MR0293695 (45 #2772)
  6. Hitczenko, Pawel; Montgomery-Smith, Stephen. A note on sums of independent random variables. Advances in stochastic inequalities (Atlanta, GA, 1997), 69--73, Contemp. Math., 234, Amer. Math. Soc., Providence, RI, 1999. MR1694763 (2000d:60080)
  7. Hitczenko, Pawel; Montgomery-Smith, Stephen. Measuring the magnitude of sums of independent random variables. Ann. Probab. 29 (2001), no. 1, 447--466. MR1825159 (2002b:60077)
  8. Jain, Naresh C.; Pruitt, William E. Lower tail probability estimates for subordinators and nondecreasing random walks. Ann. Probab. 15 (1987), no. 1, 75--101. MR0877591 (88m:60075)
  9. Klass, M. J. Toward a universal law of the iterated logarithm. I. Z. Wahrscheinlichkeitstheorie und Verw. Gebiete 36 (1976), no. 2, 165--178. MR0415742 (54 #3822)
  10. Klass, Michael J.; Nowicki, Krzysztof. An improvement of Hoffmann-Jørgensen's inequality. Ann. Probab. 28 (2000), no. 2, 851--862. MR1782275 (2001h:60029)
  11. Klass, Michael J.; Nowicki, Krzysztof. An optimal bound on the tail distribution of the number of recurrences of an event in product spaces. Probab. Theory Related Fields 126 (2003), no. 1, 51--60. MR1981632 (2004f:60038)
  12. Kolmogoroff, A. Über das Gesetz des iterierten Logarithmus.(German) Math. Ann. 101 (1929), no. 1, 126--135. MR1512520
  13. Latal a, Rafal. Estimation of moments of sums of independent real random variables. Ann. Probab. 25 (1997), no. 3, 1502--1513. MR1457628 (98h:60021)
  14. Nagaev, S. V. Some limit theorems for large deviations.(Russian) Teor. Verojatnost. i Primenen 10 1965 231--254. MR0185644 (32 #3106)
  15. Prokhorov, Yu. V. An extremal problem in probability theory. Theor. Probability Appl. 4 1959 201--203. MR0121857 (22 #12587)
















Research
Support Tool
Capture Cite
View Metadata
Printer Friendly
Context
Author Address
Action
Email Others


Home | Contents | Submissions, editors, etc. | Login | Search | ECP

Electronic Journal of Probability. ISSN: 1083-6489