A class of tests for exponentiality based on a continuum of moment conditions

Simos G. Meintanis

Kybernetika (2009)

  • Volume: 45, Issue: 6, page 946-959
  • ISSN: 0023-5954

Abstract

top
The empirical moment process is utilized to construct a family of tests for the null hypothesis that a random variable is exponentially distributed. The tests are consistent against the 'new better than used in expectation' (NBUE) class of alternatives. Consistency is shown and the limit null distribution of the test statistic is derived, while efficiency results are also provided. The finite-sample properties of the proposed procedure in comparison to more standard procedures are investigated via simulation.

How to cite

top

Meintanis, Simos G.. "A class of tests for exponentiality based on a continuum of moment conditions." Kybernetika 45.6 (2009): 946-959. <http://eudml.org/doc/37689>.

@article{Meintanis2009,
abstract = {The empirical moment process is utilized to construct a family of tests for the null hypothesis that a random variable is exponentially distributed. The tests are consistent against the 'new better than used in expectation' (NBUE) class of alternatives. Consistency is shown and the limit null distribution of the test statistic is derived, while efficiency results are also provided. The finite-sample properties of the proposed procedure in comparison to more standard procedures are investigated via simulation.},
author = {Meintanis, Simos G.},
journal = {Kybernetika},
keywords = {goodness-of-fit test; empirical moments; ageing distributions; Bahadur efficiency; goodness-of-fit test; empirical moments; ageing distributions; Bahadur efficiency},
language = {eng},
number = {6},
pages = {946-959},
publisher = {Institute of Information Theory and Automation AS CR},
title = {A class of tests for exponentiality based on a continuum of moment conditions},
url = {http://eudml.org/doc/37689},
volume = {45},
year = {2009},
}

TY - JOUR
AU - Meintanis, Simos G.
TI - A class of tests for exponentiality based on a continuum of moment conditions
JO - Kybernetika
PY - 2009
PB - Institute of Information Theory and Automation AS CR
VL - 45
IS - 6
SP - 946
EP - 959
AB - The empirical moment process is utilized to construct a family of tests for the null hypothesis that a random variable is exponentially distributed. The tests are consistent against the 'new better than used in expectation' (NBUE) class of alternatives. Consistency is shown and the limit null distribution of the test statistic is derived, while efficiency results are also provided. The finite-sample properties of the proposed procedure in comparison to more standard procedures are investigated via simulation.
LA - eng
KW - goodness-of-fit test; empirical moments; ageing distributions; Bahadur efficiency; goodness-of-fit test; empirical moments; ageing distributions; Bahadur efficiency
UR - http://eudml.org/doc/37689
ER -

References

top
  1. Moment inequalities of aging families of distributions with hypothesis testing applications, J. Statist. Plann. Infer. 92 (2001), 121–132. MR1809700
  2. Stochastic comparison of tests, Ann. Math. Statist. 31 (1960), 276–295. Zbl0201.52203MR0116413
  3. Estimation problems for fractional stable distributions, In: Trans. XXIV Internat. Seminar on Stability Problems for Stochastic Models 2004 (Andronov et al., eds.), Transport and Telecommunication Institute, Riga, Latvia, pp. 270–276. 
  4. Generalization of GMM to a continuum of moment conditions, Econometr. Theory 16 (2000), 797–834. MR1803711
  5. Simulation-based method of moments and efficiency, J. Bus. Econom. Statist. 20 (2002), 482–492. MR1945605
  6. Testing exponentiality against L -distributions, J. Statist. Plann. Infer. 64 (1997), 249–255. Zbl0914.62030MR1621616
  7. Mathematical Methods of Statistics, Princeton University Press, Princeton 1946. MR0016588
  8. Goodness-of-Fit Techniques, Marcel Dekker, New York 1986. MR0874534
  9. Lifetime distributions, IEEE Trans. Reliability 30 (1981), 457–459. 
  10. Tests for exponentiality, In: Handbook of Statistics 4: Nonparametric methods (Krishnaiah and Sen, eds.), North-Holland, Amsterdam 1984, pp. 579–611. MR0831730
  11. A test for exponentiality vs, monotone hazard alternatives derived from the empirical characteristic function. J. Roy. Statist. Soc. B48 (1986), 206–213. MR0867998
  12. Testing exponentiality against the ℒ -class of life distributions, Math. Method. Statist. 10 (2001), 232–246. MR1852070
  13. Recent and classical tests for exponentiality: a partial review with comparisons, Metrika 61 (2005), 29–45. MR2126435
  14. A class of tests for exponentiality against HNBUE alternatives, Statist. Probab. Lett. 47 (2000), 199–207. Zbl0977.62103MR1747107
  15. Efficient moment-type estimation in exponentiated laws, Math. Methods Statist. 15 (2007), 444–455. MR2301661
  16. On a nonparametric family of life distributions and its dual, J. Statist. Plann. Infer. 39 (1994), 385–397. MR1278590
  17. Moment inequalities derived from comparing life with its equilibrium form, J. Statist. Plann. Infer. 134 (2005), 303–317. MR2200060
  18. Asymptotic Efficiency of Nonparametric Tests, Cambridge University Press, New York 1995. Zbl1171.62031MR1415127
  19. Asymptotic Theory of Statistical Inference, Wiley, New York 1987. Zbl0604.62025MR0874342
  20. On optimality of the LR tests in the sence of exact slopes, I. General case. Kybernetika 25 (1989), 13–25. MR0987853
  21. On optimality of the LR tests in the sence of exact slopes, II. Application to individual distributions. Kybernetika 25 (1989), 117–135. MR0995954
  22. Handbook of Function and Generalized Function Transformations, CRC Press, New York 1996. Zbl0851.44002MR1392476

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.