Research Article
BibTex RIS Cite

Comparisons of Weighted Kolmogrov-Smirnov, Likelihood Ratio and Chi-Square Goodness of Fit Tests For The Exponential Distribution Based on the Grouped Data

Year 2008, Volume: 6 Issue: 1, 65 - 74, 15.07.2008

Abstract

In this paper, Weighted Kolmogrov-Simirnov test statistics which are used to test whether the grouped data fits to exponential distrubution proposed by Gulati and Neus (2003) are defined. These test statistics are compared with Likelihood ratio and Chi-square goodness of test statistic in terms of power under diffrent alternative distribution, group size and sample size. The simulation results showed that specially for right skewed distributuions Weighted Kolmogrov-Smirnov test statistics outperformed Pearson Chi-Square test statistics in terms of power.

References

  • Baklizi, A., (2006). Weighted Kolmogrov-Smirnov type tests for grouped Rayleigh data. Applied Mathematical Modelling 30:437-445.
  • Best, D. J., Rayner, J.C.W. (2007). Chi-Squared components for tests of fit and improved models fort he grouped exponential distribution. Computational Statistics and Data Analysis 51:3946-3954.
  • Conover, W. J. (1972). A Kolmogrov goodness-of-fit test for discontinuous distributions. Journal of the American Statistical Association 67:591-596.
  • Gulati, S., Neus, J., (2003). Goodness of fit statistics for the exponential distribution when the data grouped. Comm. Statist. Theory Methods 32, 681-700.
  • Kulldorf, G., (1961). Estimation from grouped and partially grouped samples. New York: John Wiley & Sons.
  • Pearson, K., (1900). On a criterion that a given system of deviations from the probable in the case of correlated system of variable is such that it can be reasonably supposed to have arisen from random sampling, Philos. Mag., 5th series 50 (1900) 157-175.
  • Schmid, P., (1958). On the Kolmogrov and Smirnov limit theorems for discontinuous distribution functions. Annals of Mathematical Statistics 29:1011-1027.
  • Seo, S. K., Yum, B. J. (1993). Estimation methods for the mean of the exponential distribution based on grouped and censored data. IEEE Transactions on Reliability, 42 (1):87-96.

Gruplandırılmış Verilerin Üstel Dağılıma Uyumunda Ağırlıklandırılmış Kolmogrov-Smirnov Testleri ile Olabilirlik Oranı ve Ki-Kare Testlerinin Karşılaştırılması

Year 2008, Volume: 6 Issue: 1, 65 - 74, 15.07.2008

Abstract

Bu çalışmada, gruplandırılmış verilerin üstel dağılıma uyumu için Gulati ve Neus (2003) tarafından önerilen Ağırlıklandırılmış Kolmogrov-Smirnov test istatistikleri tanıtılmıştır. Bu istatistiklerle, olabilirlik oranı ve ki-kare Uyum İyiliği test istatistikleri, farklı alternatif dağılımı, grup sayısı ve örnek çapı için güç bakımından karşılaştırılması yapılmıştır. Karşılaştırmalar sonucunda özellikle sağa çarpık dağılımlarda, Ağırlıklandırılmış Kolmogrov-Smirnov test istatistiklerinin güç bakımından performansının, Pearson ꭔve olabilirlik oranı test istatistiğine göre daha iyi olduğu görülmüştür.

References

  • Baklizi, A., (2006). Weighted Kolmogrov-Smirnov type tests for grouped Rayleigh data. Applied Mathematical Modelling 30:437-445.
  • Best, D. J., Rayner, J.C.W. (2007). Chi-Squared components for tests of fit and improved models fort he grouped exponential distribution. Computational Statistics and Data Analysis 51:3946-3954.
  • Conover, W. J. (1972). A Kolmogrov goodness-of-fit test for discontinuous distributions. Journal of the American Statistical Association 67:591-596.
  • Gulati, S., Neus, J., (2003). Goodness of fit statistics for the exponential distribution when the data grouped. Comm. Statist. Theory Methods 32, 681-700.
  • Kulldorf, G., (1961). Estimation from grouped and partially grouped samples. New York: John Wiley & Sons.
  • Pearson, K., (1900). On a criterion that a given system of deviations from the probable in the case of correlated system of variable is such that it can be reasonably supposed to have arisen from random sampling, Philos. Mag., 5th series 50 (1900) 157-175.
  • Schmid, P., (1958). On the Kolmogrov and Smirnov limit theorems for discontinuous distribution functions. Annals of Mathematical Statistics 29:1011-1027.
  • Seo, S. K., Yum, B. J. (1993). Estimation methods for the mean of the exponential distribution based on grouped and censored data. IEEE Transactions on Reliability, 42 (1):87-96.
There are 8 citations in total.

Details

Primary Language Turkish
Subjects Statistics
Journal Section Research Articles
Authors

Hamza Gamgam

Esra Yiğit This is me

Publication Date July 15, 2008
Published in Issue Year 2008 Volume: 6 Issue: 1

Cite

APA Gamgam, H., & Yiğit, E. (2008). Gruplandırılmış Verilerin Üstel Dağılıma Uyumunda Ağırlıklandırılmış Kolmogrov-Smirnov Testleri ile Olabilirlik Oranı ve Ki-Kare Testlerinin Karşılaştırılması. İstatistik Araştırma Dergisi, 6(1), 65-74.