Abstract
In this paper we propose the Directed Goodness of Fit (DGoF) test and the Directed test of Homogeneity (DHom). These types of tests are constructed based on a particular type of discrepancy measures called weighted (or directed) divergences. These measures allow the researcher to focus on specific subsets of the support without, at the same time, losing the information of the others. The performance of the proposed tests examined for a variety of distributions via extensive Monte Carlo simulations. Also, comparisons with the most known tests in the literature are placed to validate the usefulness of the proposed results. Finally, we achieve significantly more powerful tests as compared to the classical ones with comparable error rates.
Similar content being viewed by others
References
Avlogiaris G, Micheas A, Zografos K (2016) On testing local hypotheses via local divergence. Stat Methodol 31:20–42
Balkema AA, De Haan L (1974) Residual life time at great age. Ann Probab 2:792–804
Barbu VS, Karagrigoriou A, Preda V (2018) Entropy and divergence rates for Markov chains: 2. The weighted case. Proc Rom Acad Series A 18(4):293–300
Black F, Scholes M (1973) The pricing of options and corporate liabilities. J Polit Econ 81(3):637–654
Cavanaugh JE (2004) Criteria for linear model selection based on Kullback’s symmetric divergence. Austral N Z J Stat 46(2):257–274
Cressie N, Read TR (1984) Multinomial goodness-of-fit tests. J R Stat Soc Ser B 46(3):440–464
Danielsson J (2011) Financial risk forecasting: the theory and practice of forecasting market risk with implementation in R and Matlab, vol 588. Wiley, Hoboken
Dik J, De Gunst M (1985) The distribution of general quadratic forms in norma. Stat Neerl 39(1):14–26
Eberlein E, Keller U (1995) Hyperbolic distributions in finance. Bernoulli 1(3):281–299
Frank O, Menéndez M, Pardo L (1998) Asymptotic distributions of weighted divergence between discrete distributions. Commun Stat 27(4):867–885
Gkelsinis T, Karagrigoriou A (2020) Theoretical aspects on measures of directed information with simulations. Mathematics 8(4):587
Guiaşu S (1971) Weighted entropy. Rep Math Phys 2(3):165–179
Kapur JN (1994) Measures of information and their applications. Wiley, Hoboken
Knight J, Satchell S (2001) Return distributions in finance. Elsevier, Amsterdam
Landaburu E, Pardo L (2000) Goodness of fit tests with weights in the classes based on (\(h\),\(phi\))-divergences. Kybernetika 36(5):589–602
Li DX (2000) On default correlation: a copula function approach. J Fixed Income 9(4):43–54
Mandelbrot B (1961) Stable Paretian random functions and the multiplicative variation of income. Econometrica 29:517–543
Mattheou K, Lee S, Karagrigoriou A (2009) A model selection criterion based on the BHHI measure of divergence. J Stat Plan Inference 139(2):228–235
Pardo L (2018) Statistical inference based on divergence measures. CRC Press, Boca Raton
Parodi P (2014) Pricing in general insurance. CRC Press, Boca Raton
Pickands J III (1975) Statistical inference using extreme order statistics. Ann Stat 3(1):119–131
Rao JN, Scott AJ (1981) The analysis of categorical data from complex sample surveys: chi-squared tests for goodness of fit and independence in two-way tables. J Am Stat Assoc 76(374):221–230
Romao X, Delgado R, Costa A (2009) An empirical power comparison of univariate goodness-of-fit tests for normality. J Stat Comput Simul 80:545–591
Toma A (2014) Model selection criteria using divergences. Entropy 16(5):2686–2698
Wystup U (2003) The market price of one-touch options in foreign exchange markets. Deriv Week 12(13):8–9
Zografos K, Ferentinos K, Papaioannou T (1990) Divergence statistics: sampling properties and multinomial goodness of fit and divergence tests. Commun Stat 19(5):1785–1802
Acknowledgements
The authors wish to express their appreciation to the anonymous referees for their valuable comments and recommendations. The first author acknowledges the Region of Normandy, France, for the valuable financial support during his PhD.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gkelsinis, T., Karagrigoriou, A. & Barbu, V.S. Statistical inference based on weighted divergence measures with simulations and applications. Stat Papers 63, 1511–1536 (2022). https://doi.org/10.1007/s00362-022-01286-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-022-01286-z
Keywords
- Directed information
- Goodness of fit test
- Homogeneity test
- Information measures
- Divergence
- Weighted divergence