Abstract
Recently, Nair et al. (Stat Pap 52:893–909, 2011) studied Chernoff distance for truncated distributions in univariate setup. The present paper addresses the question of extending the concept of Chernoff distance to bivariate setup with focus on residual as well as past lifetimes. This measure is extended to conditionally specified models of two components having possibly different ages or failed at different time instants. We provide some bounds using likelihood ratio order and investigate several properties of conditional Chernoff distance. The effect of monotone transformation on this conditional measure has also been examined. Moreover, we study conditional Chernoff distance in context of weighted model.
Similar content being viewed by others
References
Adhikari BP, Joshi DD (1956) Distance, discrimination et rsum exhaustif. Pubis Inst Starist Unie Paris 5:57–74
Ahmadi J, Di Crescenzo A, Longobardi M (2015) On dynamic mutual information for bivariate lifetimes. Adv Appl Probab 47(4):1157–1174
Ali SM, Silvey SD (1966) A general class of coefficients of divergence of one distribution from another. J R Stat Soc Ser B 28:131–142
Arnold BC, Castillo E, Sarabia JM (1999) Conditional specification of statistical models. Springer, New York
Burbea J, Rao CR (1982) On the convexity of some divergence measures based on entropy functions. IEEE Trans Inf Theory 28:489–495
Chernoff H (1952) Measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann Math Stat 23:493–507
Cox DR (1959) The analysis of exponentially distributed lifetimes with two types of failure. J R Stat Soc Ser B 21:411–421
Csiszár I (1967) Information-type measures of difference of probability distributions and indirect observations. Stud Sci Math Hung 2:299–318
Ebrahimi N, Kirmani SNUA, Soofi ES (2007) Multivariate dynamic information. J Multivar Anal 98:328–349
Fisher RA (1934) The effect of methods of ascertainment upon the estimation of frequencies. Ann Eugen 6:13–25
Gumbel EJ (1961) Bivariate logistic distributions. J Am Stat Assoc 56:335–349
Gupta RC, Gupta RD, Gupta PL (1998) Modeling failure time data by Lehman alternatives. Commun Stat Theory Methods 27:887–904
Jain K, Nanda AK (1995) On multivariate weighted distributions. Commun Stat Theory Methods 24(10):2517–2539
Johnson NL, Kotz S (1975) A vector multivariate hazard rate. J Multivar Anal 5:53–66
Kailath T (1967) The divergence and Bhattacharyya distance measures in signal selection. IEEE Trans Commun Technol 5(1):52–60
Kamps U (1989) Hellinger distances and \(\alpha \)-entropy in a one-parameter class of density functions. Stat Pap 30:263–269
Kapur JN (1984) A comparative assessment of various measures of directed divergences. Adv Manag Stud 3:1–16
Kullback S (1959) Information theory and statistics. Wiley, New York
Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22(1):79–86
Kundu A, Kundu C (2016) Bivariate extension of (dynamic) cumulative past entropy. Commun Stat Theory Methods. doi:10.1080/03610926.2015.1080838
Mahalanobis PC (1936) On the generalized distance in statistics. Proc Natl Inst Sci 2:49–55
Nair NU, Asha G (2008) Some characterizations based on bivariate reversed mean residual life. ProbStat Forum 1:1–14
Nair KRM, Sankaran PG, Smitha S (2011) Chernoff distance for truncated distributions. Stat Pap 52:893–909
Navarro J, Sunoj SM, Linu MN (2011) Characterizations of bivariate models using dynamic Kullback–Leibler discrimination measures. Stat Probab Lett 81:1594–1598
Navarro J, Sunoj SM, Linu MN (2014) Characterizations of bivariate models using some dynamic conditional information divergence measures. Commun Stat Theory Methods 43:1939–1948
Nielsen F (2013) An information-geometric characterization of chernoff information. IEEE Signal Proc Lett 20(3):269–272
Patil GP, Rao CR, Ratnaparkhi MV (1987) Bivariate weighted distributions and related applications. Technical report, Centre for Statistical Ecology and Environmental Statistics
Rao CR (1952) Advanced statistical methods in biometric research. Wiley, New York
Rao CR (1965) On discrete distributions arising out of methods of ascertainment. In: Patil GP (ed) Classical and contagious discrete distributions. Permagon Press, Oxford and Statistical Publishing Society, Calcutta, pp 320–332
Roy D (2002) A characterization of model approach for generating bivariate life distributions using reversed hazard rates. J Jpn Stat Soc 32(2):239–245
Rajesh G, Abdul-Sathar EI, Nair KRM (2014) Bivariate extension of dynamic cumulative residual entropy. Stat Methodol 16:72–82
Sankaran PG, Nair NU (1993) A bivariate Pareto model and its applications to reliability. Nav Res Logist 40:1013–1020
Sankaran PG, Sreeja VN (2007) Proportional hazards model for multivariate failure time data. Commun Stat Theory Methods 36:1627–1641
Silber J (1989) Gini’s concentration index and the measurement of the distance between relative price vectors. Stat Pap 30:231–238
Sunoj SM, Linu MN (2012) Dynamic cumulative residual Renyi’s entropy. Statistics 46(1):41–56
Shaked M, Shanthikumar JG (2007) Stochastic orders. Springer, New York
Zahedi H (1985) Some new classes of multivariate survival functions. J Stat Plan Inference 11:171–188
Acknowledgments
We are thankful to the Editor-in-Chief of the journal and anonymous reviewers for their valuable comments and suggestions leading to an improved version of the manuscript. The financial support (Ref. No. SR/FTP/MS-016/2012) rendered by the Department of Science and Technology, Government of India is acknowledged with thanks by C. Kundu for carrying out this research work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ghosh, A., Kundu, C. Chernoff distance for conditionally specified models. Stat Papers 59, 1061–1083 (2018). https://doi.org/10.1007/s00362-016-0804-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-016-0804-5
Keywords
- Chernoff distance
- Conditionally specified model
- Conditional proportional (reversed) hazard rate model
- Likelihood ratio order
- Weighted model