SciELO - Scientific Electronic Library Online

 
vol.35 issue3On the Entropy of Written SpanishAn Empirical Comparison of EM Initialization Methods and Model Choice Criteria for Mixtures of Skew-Normal Distributions author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Revista Colombiana de Estadística

Print version ISSN 0120-1751

Rev.Colomb.Estad. vol.35 no.3 Bogotá July/Dec. 2012

 

On the Use of Ranked Set Samples in Entropy Based Test of Fit for the Laplace Distribution

Uso de muestras de rango ordenado en una prueba de ajuste basada en entropía para la distribución Laplace

MAHDI MAHDIZADEH1

1Hakim Sabzevari University, Department of Statistics, Sabzevar, Iran. Assistant Professor. Email: mahdizadeh.m@live.com, noniid@yahoo.com


Abstract

Statistical methods based on ranked set sampling (RSS) often lead to marked improvement over analogous methods based on simple random sampling (SRS). Entropy has been influential in the development of measures of fit of parametric models to the data. This article develops goodness-of-fit tests of the Laplace distribution based on sample entropy when data are collected according to some RSS-based schemes. For each design, critical values of the corresponding test statistic are estimated, by means of simulation, for some sample sizes. A Monte Carlo study on the power of the new tests is performed for several alternative distributions and sample sizes in order to compare our proposal with available method in SRS. Simulation results show that RSS and its variations lead to tests giving higher power than the test based on SRS.

Key words: Entropy estimation, Goodness-of-fit test, Ranked set sampling.


Resumen

Los métodos estadísticos basados en muestreo de rango ordenado a menudo son una considerable mejora que el muestreo aleatorio simple. La medida de entropía ha sido influencial en el desarrollo de medidas de ajuste de modelos paramétricos. Este artículo propone pruebas de bondad de ajuste de la distribución Laplace basada en la entropía muestral cuando se usan estructuras basadas en muestras de rango ordenado. Para cada diseño, los valores críticos del correspondiente estadístico de prueba son estimados por medio de simulaciones para diferentes tamaños de muestra. Un estudio de Monte Carlo de la potencia de los nuevos tests es implementado para diferentes distribuciones alternas y tamaños de muestra con el fin de comparar el método propuesto con otros disponibles. La simulación muestra que el muestreo de rango ordenado y sus variaciones brindan mayor potencia que los métodos basados en muestreo aleatorio simple.

Palabras clave: entropía, muestreo rango ordenado, prueba de bondad de ajuste.


Texto completo disponible en PDF


References

1. Al-Saleh, M. F. & Al-Kadiri, M. (2000), 'Double ranked set sampling', Statistics & Probability Letters 48, 205-212.         [ Links ]

2. Al-Saleh, M. F. & Al-Omari, A. I. (2002), 'Multistage ranked set sampling', Journal of Statistical Planning and Inference 102, 273-286.         [ Links ]

3. Chen, Z., Bai, Z. & Sinha, B. K. (2004), Ranked set sampling: Theory and Applications, Springer, New York.         [ Links ]

4. Choi, B. & Kim, K. (2006), 'Testing goodness-of-fit for laplace distribution based on maximum entropy', Statistics 40, 517-531.         [ Links ]

5. Dudewicz, E. J. & van der Meulen, E. C. (1981), 'Entropy-based tests of uniformity', Journal of the American Statistical Association 76, 967-974.         [ Links ]

6. Ebrahimi, N., Pflughoeft, K. & Soofi, E. S. (1994), 'Two measures of sample entropy', Statistics & Probability Letters 20, 225-234.         [ Links ]

7. Gokhale, D. V. (1983), 'On the entropy-based goodness-of-fit tests', Computational Statistics & Data Analysis 1, 157-165.         [ Links ]

8. Grzegorzewski, P. & Wieczorkowski, R. (1999), 'Entropy based goodness-of-fit test for exponentiality', Communications in Statistics: Theory and Methods 28, 1183-1202.         [ Links ]

9. Kotz, S., Kozubowski, T. J. & Podg\'orski, K. (), The Laplace Distribution and Generalizations: A Revisit with Applications to Communications, Economics, Engineering, and Finance, Birkh\auser.         [ Links ]

10. Mahdizadeh, M. & Arghami, N. R. (2010), 'Efficiency of ranked set sampling in entropy estimation and goodness-of-fit testing for the inverse gaussian law', Journal of Statistical Computation and Simulation 80, 761-774.         [ Links ]

11. McIntyre, G. A. (1952), 'A method of unbiased selective sampling using ranked sets', Australian Journal of Agricultural Research 3, 385-390.         [ Links ]

12. Mudholkar, G. S. & Tian, L. (2002), 'An entropy characterization of the inverse gaussian distribution and related goodness-of-fit test', Journal of Statistical Planning and Inference 102, 211-221.         [ Links ]

13. Shannon, C. E. (1948), 'A mathematical theory of communications', Bell System Technical Journal 27, 379-423.         [ Links ]

14. Stokes, S. L. & Sager, T. W. (1988), 'Characterization of a ranked-set sample with application to estimating distribution function', Journal of the American Statistical Association 83, 374-381.         [ Links ]

15. Takahasi, K. & Wakimoto, K. (1968), 'On unbiased estimates of the population mean based on the sample stratified by means of ordering', Annals of the Institute of Statistical Mathematics 21, 249-255.         [ Links ]

16. Vasicek, O. (1976), 'A test of normality based on sample entropy', Journal of the Royal Statistical Society Series B 38, 54-59.         [ Links ]


[Recibido en noviembre de 2010. Aceptado en octubre de 2012]

Este artículo se puede citar en LaTeX utilizando la siguiente referencia bibliográfica de BibTeX:

@ARTICLE{RCEv35n3a07,
    AUTHOR  = {Mahdizadeh, Mahdi},
    TITLE   = {{On the Use of Ranked Set Samples in Entropy Based Test of Fit for the Laplace Distribution}},
    JOURNAL = {Revista Colombiana de Estadística},
    YEAR    = {2012},
    volume  = {35},
    number  = {3},
    pages   = {443-455}
}