Abstract
We consider the problem of providing the exact distribution of the likelihood ratio test (LRT) statistic for testing the homogeneity of scale parameters of \( k \ge 2 \) two-parameter exponential distributions. To this end, we apply the Millen inverse transform and the Jacobi polynomial expansion to the moments of LRT statistic. We consider the problem when the data are either complete or censored under the different kinds of Type II censoring, such as the Type II right, progressively Type II right, and double Type II censoring schemes. We also discuss the exact null distribution of the LRT when the data are censored under the Type I censoring scheme.
Similar content being viewed by others
References
Alexits G (1961) Convergence problems of orthogonal series. Pergamon press, New York
Alvarez-Andradea S, Balakrishnan N, Bordes L (2007) Homogeneity tests based on several progressively Type-II censored samples. J Multivar Anal 98:1195–1213
Bain LJ (1978) Statistical Analysis of Reliability and Life-Testing Models. Marcel Dekker, New York
Balakrishnan N, Aggarwala R (2000) Progressive censoring: theory, methods, and applications, series title: statistics for industry and technology. Springer, New York
Balakrishnan N, Basu AP (1995) Exponential distribution: theory, methods and applications. CRC Press, Boca Raton
Balakrishnan N, Stehlik M (2015) Likelihood testing with censored and missing duration data. J Stat Theory Pract 9:2–22
Balakrishnan N, Han D, Iliopoulos G (2011) Exact inference for progressively Type-I censored exponential failure data. Metrika 73:335–358
Boik RJ (1993) Null distribution of a statistic for testing sphericity and additivity: a Jacobi polynomial expansion. Appl Stat 42(3):567–584
Bolkhovskaya OV, Maltsev AA, LoPresti L, Sellone F (2001) Approximation of the distribution function of a generalized likelihood ratio for the detection of spatial partially coherent signals in the short sample case. In: Institute of electrical and electronics engineers (IEEE) international conference on electromagnetics in advanced applications, Torino, 10–14 September
Cheng C, Chen J, Bai J (2013) Exact inferences of the two-parameter exponential distribution and Pareto distribution with censored data. J Appl Stat 40(7):1464–1479
Cole KN, Nagarsenker PB, Nagarsenker BN (1987) A test for equality of exponential distributions based on Type-II censored samples. IEEE Trans Reliab 36(1):94–97
Derksen RW, Sullivan PJ (1990) Moment approximations for probability density functions. Combust Flame 81:378–391
Economou P, Stehlik M (2014) On small samples testing for frailty through homogeneity test. Commun Stat Simul Comput 44(1):20–65
Hill N, Padmanabhan A, Puri ML (1988) Adaptive nonparametric procedures and applications. Appl Stat 37(2):205–218
Hsieh HK (1986) An exact test for comparing location parameters of k exponential distributions with unequal scales based on Type II censored data. Technometrics 28(2):157–164
Kalinin VM, Shalaevskii VO (1971) Investigations in classical problems of probability theory and mathematical statistics: part I. Consultants Bureau, New York
Luke YL (1969) The special functions and their approximations, vol I. Academic Press, New York
Malekzadeh A, Jafari AA (2018) Testing equality of quantiles of two-parameter exponential distributions under progressive Type-II censoring. J Stat Theory Pract 12(4):776–793
Maurya V, Goyal A, Gill AN (2011) Simultaneous testing for the successive differences of exponential location parameters under heteroscedasticity. Stat Probab Lett 81(10):1507–1517
Nagarsenker BN (1976) Exact non-null distribution of the likelihood ratio criteria for covariance matrix. Can J Stat 4(2):237–254
Nagarsenker PB (1980) On a test of equality of several exponential survival distributions. Biometrika 67(2):475–478
Nagarsenker BN, Nagarsenker PB (1985) Distribution of LRT for testing the equality of several 2-parameter exponential distributions. IEEE Trans Reliab 34:65–68
Nagarsenker PB, Nagarsenker BN (1986) On a test of equality of scale parameters of several exponential distributions. Commun Stat Simul Comput 15(2):497–504
Nagarsenker PB, Nagarsenker BN (1991) On a modified test of equality of scale parameters of exponential distributions. Commun Stat Theory Methods 20(2):735–745
Nair US (1940) Application of factorial series in the study of distribution laws in statistics. Sankhya 5:175
Proschan F (1963) Theoretical explanation of observed decreasing failure rate. Technometrics 5:375–383
Provost SB (2005) Moment-based density approximants. Math J 9(4):727–756
Reinking JT (2002) Orthogonal series representation of probability density and distribution functions. Math J. https://www.mathematica-journal.com/issue/v8i3/features/reinking/index.html
Sadooghi-Alvandi SM, Malekzadeh A (2013) A note on testing homogeneity of the scale parameters of several inverse Gaussian distributions. Stat Probab Lett 83:1844–1848
Singh N (1985) A simple and asymptotically optimal test for the equality of k (k ≥2) exponential distributions based on type II censored samples. Commun Stat Theory Methods 14:1615–1625
Singh N, Cheng I (1986) Tests for equality of location & scale parameters of exponential distributions with Type-II censoring. IEEE Trans Reliab 35(2):208–211
Singh RS, Kumar N (2011) Lower confidence bounds for the probabilities of correct selection. J Probab Stat. https://doi.org/10.1155/2011/765058
Stehlik M (2003) Distributions of exact tests in the exponential family. Metrika 57:145–164
Stehlik M (2006) Exact likelihood ratio scale and homogeneity testing of some loss processes. Stat Probab Lett 76:19–26
Stehlik M (2008) Homogeneity and scale testing of generalized gamma distribution. Reliab Eng Syst Saf Reliab 93:1809–1813
Stehlik M (2009) Scale testing in small samples with missing time-to-failure information. Int J Reliab Qual Saf Eng 16(6):1–13
Stehlik M, Wagner H (2011) Exact likelihood ratio testing for homogeneity of exponential distribution. Commun Stat Simul Comput 40(5):663–684
Thiagarajah KR (1995) Homogeneity tests for scale parameters of 2-parameter exponential populations under time censoring. IEEE Trans Reliab 44(2):297–301
Thiagarajah KR, Paul SR (1990) Testing for the equality of scale parameters of k exponential populations based on complete and Type II censored samples. Commun Stat Simul Computs 19(3):891–902
Viveros R, Balakrishnan N (1994) Interval estimation of parameters of life from progressively censored data. Technometrics 36(1):84–91
Acknowledgements
The authors would like to thank referees for their constructive comments. The first author would like to thank the Research Council of Shiraz University.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All 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
Appendix
Appendix
Proof of Lemma 1
Note that \( \varvec{Z} = \left( {Z_{1} , \ldots ,Z_{k} } \right) = \left( {\frac{{Y_{1} }}{{\mathop \sum \nolimits_{i = 1}^{k} Y_{i} }}, \ldots ,\frac{{Y_{k} }}{{\mathop \sum \nolimits_{i = 1}^{k} Y_{i} }}} \right) \) has a Dirichlet distribution with parameter \( (\theta_{1} - 1, \ldots ,\theta_{k} - 1) \). Therefore, the \( h \)th moment of \( L \) under \( H_{0} \) is
Now, let \( V_{i} = \sigma_{i} Y_{i} /\mathop \sum \nolimits_{i = 1}^{k} \sigma_{i} Y_{i} \), \( i = 1, \ldots ,k \). It is easily verified that \( Y_{i} = (V_{i} /\sigma_{i} )/\mathop \sum \nolimits_{i = 1}^{k} (V_{i} /\sigma_{i} ) \) and thus the joint density function of \( \varvec{V} = (V_{1} , \ldots ,V_{k} ) \) is
Therefore, the \( h \)th moment of \( L \) is
This completes the proof.□
Proof of Theorem 1
Here, we present a sketch of proof. For more detail, one can refer to Nagarsenker (1976). Let \( f_{L} (.) \) denote the density function of \( L \). If \( f_{L} (.) \) can be obtained in a closed form, then \( F_{L} (.) \) is obtained directly. By applying the Mellin inverse transform to \( E_{{H_{0} }} (L^{h} ) \) and changing variable \( h + {{\Theta }} = t \), we have
where \( \phi \left( t \right) = (\mathop \prod \nolimits_{i = 1}^{k} {{\Gamma }}\left( {\theta_{i} t/{{\Theta }} - 1} \right)\left( {{{\Theta }}/\theta_{i} } \right)^{{\theta_{i} t/{{\Theta }}}} )/{{\Gamma }}\left( {t - k} \right) \). We also generally have\( \log {{\Gamma }}(x + a) = \frac{1}{2}\log \left( {2\pi } \right) + \left( {x + a - \frac{1}{2}} \right)\log \left( x \right) - x - \mathop \sum \nolimits_{r = 1}^{m} \frac{{\left( { - 1} \right)^{r} B_{r + 1} \left( a \right)}}{{r\left( {r + 1} \right)x^{r} }} + R_{m + 1} \left( x \right), \)where \( R_{m} (x) \) is the remainder such that \( \left| {R_{m} \left( x \right)} \right| \le C/|x^{m} | \), \( C \) is a constant independent of \( x \) and \( B_{r} (a) \) is the Bernoulli polynomial of degree \( r \) and order one; see Nagarsenker (1976). Therefore, the expansion of \( \log (\phi \left( t \right)) \) is
where \( v = (k - 1)/2 \). By letting \( m \to \infty \),e have
where \( \beta_{j} \)s are obtained recursively as \( \beta_{j} = \frac{1}{j}\mathop \sum \nolimits_{s = 1}^{j} s \alpha_{s} \beta_{j - s} \) with \( \beta_{0} = 1 \) in which
see Kalinin and Shalaevskii (1971). Note that \( \left( {2\pi } \right)^{ - v} \mathop \prod \nolimits_{i = 1}^{k} \left( {\theta_{i} /{{\Theta }}} \right)^{1.5} \phi \left( t \right) = O\left( {t^{ - v} } \right) \). Therefore, \( \left( {2\pi } \right)^{ - v} \mathop \prod \nolimits_{i = 1}^{k} \left( {\theta_{i} /{{\Theta }}} \right)^{1.5} \phi \left( t \right) \) can be expanded as a factorial series of the form
for any \( a \ge 0 \); see Nair (1940). The coefficient \( R_{r} \) can be obtained by equating the coefficients of the two series (A.1) and (A.2). In this regard, note that \( \log ({{\Gamma }}(t)/{{\Gamma }}(t + r + v)) \) can be expanded as \( - \left( {v + n} \right)\log \left( t \right) + \sum\nolimits_{j = 1}^{\infty } {A_{r,j} } /t^{j} \) where
Therefore, we can write \( \frac{\varGamma \left( t \right)}{{\varGamma \left( {t + r + v} \right)}} = t^{{ - \left( {v + r} \right)}} \left\{ {1 + \sum\nolimits_{j = 1}^{\infty } {\frac{{C_{r,j} }}{{t^{j} }}} } \right\} \) where \( C_{r,j} = \frac{1}{j}\sum\nolimits_{q = 1}^{j} q A_{r,q} C_{r,j - q} \) with \( C_{r,0} = 1 \). Finally, the coefficients \( R_{r} \) are obtained recursively by \( \sum\nolimits_{j = 0}^{i} {R_{i - j} } C_{i - j,j} = \beta_{i} \) with \( R_{0} = 1 \). Now, \( f_{L} (l) \) can be obtained by integrating term by term of (A.2) since a factorial series is uniformly convergent in a half-plane; see Nagarsenker (1976). Therefore, we have
However, \( \frac{1}{2\pi i}\mathop \int \nolimits_{{{{\Theta }} - i\infty }}^{{{{\Theta }} + i\infty }} l^{ - t} {{\Gamma }}(t)/{{\Gamma }}\left( {t + r + v} \right) dt = l\left( {1 - l} \right)^{v + r - 1} /{{\Gamma }}(v + r) \); see Nagarsenker (1976). This completes the proof.□
Proof of Theorem 2
Note that the support of \( L \) is \( (0, 1) \) since \( {{\Lambda }} \) is the LRT statistic. By matching the first two moments of Beta \( (p,q) \) random variable and \( L \), we have
In this case, it can be easily verified that \( c_{1} = c_{2} = 0 \). It completes the proof.□
Rights and permissions
About this article
Cite this article
Kharrati-Kopaei, M., Malekzadeh, A. On the exact distribution of the likelihood ratio test for testing the homogeneity of scale parameters of several two-parameter exponential distributions: complete and censored samples. Metrika 82, 409–427 (2019). https://doi.org/10.1007/s00184-018-00704-3
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-018-00704-3
Keywords
- Double Type II censoring
- Jacobi polynomial expansion
- Likelihood ratio test
- Millen inverse transform
- Progressive Type II censoring
- Type I censoring
- Two-parameter exponential