Electronic Journal of Statistics

Hypothesis testing near singularities and boundaries

Jonathan D. Mitchell, Elizabeth S. Allman, and John A. Rhodes

Full-text: Open access

Enhanced PDF (1616 KB)

Abstract

The likelihood ratio statistic, with its asymptotic $\chi ^{2}$ distribution at regular model points, is often used for hypothesis testing. However, the asymptotic distribution can differ at model singularities and boundaries, suggesting the use of a $\chi ^{2}$ might be problematic nearby. Indeed, its poor behavior for testing near singularities and boundaries is apparent in simulations, and can lead to conservative or anti-conservative tests. Here we develop a new distribution designed for use in hypothesis testing near singularities and boundaries, which asymptotically agrees with that of the likelihood ratio statistic. For two example trinomial models, arising in the context of inference of evolutionary trees, we show the new distributions outperform a $\chi ^{2}$.

Note

When this article was first made public, on June 28, 2019, its page numbering was incorrect (pp. 1250–1293). The article’s page numbers were corrected to 2150–2193 on July 30, 2019.

Article information

Source
Electron. J. Statist., Volume 13, Number 1 (2019), 2150-2193.

Dates
Received: June 2018
First available in Project Euclid: 28 June 2019

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1561687407

Digital Object Identifier
doi:10.1214/19-EJS1576

Mathematical Reviews number (MathSciNet)
MR3980955

Zentralblatt MATH identifier
07089017

Subjects
Primary: 62E17: Approximations to distributions (nonasymptotic)
Secondary: 92D15: Problems related to evolution

Keywords
Hypothesis testing singularity boundary likelihood ratio statistic chi-squared phylogenomics coalescent

Rights
Creative Commons Attribution 4.0 International License.

Citation

Mitchell, Jonathan D.; Allman, Elizabeth S.; Rhodes, John A. Hypothesis testing near singularities and boundaries. Electron. J. Statist. 13 (2019), no. 1, 2150--2193. doi:10.1214/19-EJS1576. https://projecteuclid.org/euclid.ejs/1561687407


Export citation

References

  • [1] Allman, E. S., Degnan, J. H. and Rhodes, J. A. (2011). Identifying the Rooted Species Tree from the Distribution of Unrooted Gene Trees under the Coalescent., J. Math Biol. 6 833–862.
    Zentralblatt MATH: 1230.92033
    Digital Object Identifier: doi:10.1007/s00285-010-0355-7
  • [2] Andrews, D. W. K. (2000). Inconsistency of the bootstrap when a parameter is on the boundary of the parameter space., Econometrica 68 399–405.
    Mathematical Reviews (MathSciNet): MR1748009
    Zentralblatt MATH: 1015.62044
    Digital Object Identifier: doi:10.1111/1468-0262.00114
  • [3] Andrews, D. W. K. and Guggenberger, P. (2009a). Hybrid and size-corrected subsampling methods., Econometrica 77 721–762.
    Zentralblatt MATH: 1176.62117
    Digital Object Identifier: doi:10.3982/ECTA7015
  • [4] Andrews, D. W. K. and Guggenberger, P. (2009b). Incorrect Asymptotic size of subsampling procedures based on post-consistent model selection estimators., J. Econometrics 152 19–27.
    Zentralblatt MATH: 06604110
    Digital Object Identifier: doi:10.1016/j.jeconom.2009.02.001
  • [5] Andrews, D. and Guggenberger, P. (2010). Asymptotic size and a problem with subsampling and with the m out of n bootstrap., Econometric Theory 26 426–468.
    Zentralblatt MATH: 1185.62044
    Digital Object Identifier: doi:10.1017/S0266466609100051
  • [6] Bartolucci, F. (2006). Likelihood inference for a class of latent Markov models under linear hypotheses on the transition probabilities., J. R. Statist. Soc. B 68 155–178.
    Mathematical Reviews (MathSciNet): MR2188980
    Zentralblatt MATH: 1100.62078
    Digital Object Identifier: doi:10.1111/j.1467-9868.2006.00538.x
  • [7] Bartolucci, F., Forcina, A. and Dardanoni, V. (2001). Positive quadrant dependence and marginal modeling in two-way tables with ordered margins., J. Am. Stat. Assoc. 96 1497–1505.
    Mathematical Reviews (MathSciNet): MR1946593
    Zentralblatt MATH: 1073.62542
    Digital Object Identifier: doi:10.1198/016214501753382390
  • [8] Berger, R. L. and Boos, D. D. (1994). P values maximized over a confidence set for nuisence parameters., J. Am. Stat. Assoc. 89 1012–1016.
    Mathematical Reviews (MathSciNet): MR1294746
    Zentralblatt MATH: 0804.62018
  • [9] Chernoff, H. (1954). On the distribution of the likelihood ratio., The Annals of Mathematical Statistics 25 573–578.
    Zentralblatt MATH: 0056.37102
    Digital Object Identifier: doi:10.1214/aoms/1177728725
    Project Euclid: euclid.aoms/1177728725
  • [10] Cressie, N. A. and Read, T. R. (1984). Multinomial Goodness-of-Fit Tests., Journal of the Royal Statistical Society. Series B (Methodological) 440–464.
    Zentralblatt MATH: 0571.62017
    Digital Object Identifier: doi:10.1111/j.2517-6161.1984.tb01318.x
  • [11] Cressie, N. A. and Read, T. R. (1989). Pearson’s $X^2$ and the Loglikelihood Ratio Statistic $G^2$: A Comparative Review., International Statistical Review/Revue Internationale de Statistique 19–43.
    Mathematical Reviews (MathSciNet): MR0494615
    Zentralblatt MATH: 0707.62105
    Digital Object Identifier: doi:10.2307/1403315
  • [12] Degnan, J. H. and Rosenberg, N. A. (2009). Gene tree discordance, phylogenetic inference and the multispecies coalescent., Trends in Ecology & Evolution 24 332–340.
  • [13] Drton, M. (2009). Likelihood Ratio Tests and Singularities., The Annals of Statistics 979–1012.
    Zentralblatt MATH: 1196.62020
    Digital Object Identifier: doi:10.1214/07-AOS571
    Project Euclid: euclid.aos/1236693157
  • [14] Durand, E. Y., Patterson, N., Reich, D. and Slatkin, M. (2011). Testing for Ancient Admixture between Closely Related Populations., Mol Biol Evol. 28 2239–2252.
  • [15] Florescu, I. (2014)., Probability and Stochastic Processes. John Wiley & Sons.
    Zentralblatt MATH: 1303.60001
  • [16] Gaither, J. and Kubatko, L. (2016). Hypothesis tests for phylogenetic quartets, with applications to coalescent-based species tree inference., Journal of Theoretical Biology 408 179–186.
    Zentralblatt MATH: 1352.92102
    Digital Object Identifier: doi:10.1016/j.jtbi.2016.08.013
  • [17] Green, R. E., Krause, J., Briggs, A. W., Maricic, T., Stenzel, U. et al. (2010). A Draft Sequence of the Neandertal Genome., Science 328 710–722.
  • [18] Gu, X. and Li, W.-H. (1996). Bias-corrected paralinear and LogDet distances and tests of molecular clocks and phylogenies under nonstationary nucleotide frequencies., Molecular Biology and Evolution 13 1375–1383.
  • [19] Massingham, T. and Goldman, N. (2007). Statistics of the log-det estimator., Molecular Biology and Evolution 24 2277–2285.
  • [20] McCloskey, A. (2017). Bonferroni-based size-correction for nonstandard testing problems., J. Econometrics 200 17–35.
    Zentralblatt MATH: 1388.62371
    Digital Object Identifier: doi:10.1016/j.jeconom.2017.05.001
  • [21] Miller, J. J. (1977). Asymptotic properties of maximum likelihood estimates in the mixed model of the analysis of variance., The Annals of Statistics 746–762.
    Zentralblatt MATH: 0406.62017
    Digital Object Identifier: doi:10.1214/aos/1176343897
    Project Euclid: euclid.aos/1176343897
  • [22] Neyman, J. and Pearson, E. S. (1933). On the Problem of the Most Efficient Tests of Statistical Hypotheses., Philosophical Transactions of the Royal Society of London. Series A, Containing Papers of a Mathematical or Physical Character 231 289–337.
    Zentralblatt MATH: 59.1163.02
    Digital Object Identifier: doi:10.1098/rsta.1933.0009
  • [23] Olver, F. W. (2010)., NIST handbook of mathematical functions hardback and CD-ROM. Cambridge University Press.
  • [24] Pamilo, P. and Nei, M. (1988). Relationships between gene trees and species trees., Mol Biol Evol. 5 568–583.
  • [25] Rannala, B. and Yang, Z. (2003). Bayes Estimation of Species Divergence Times and Ancestral Population Sizes Using DNA Sequences From Multiple Loci., Genetics 164 1645–1656.
  • [26] Rosenberg, N. A. (2002). The probability of topological concordance of gene trees and species trees., Theoretical Population Biology 61 225–247.
    Zentralblatt MATH: 1040.92032
    Digital Object Identifier: doi:10.1006/tpbi.2001.1568
  • [27] Self, S. G. and Liang, K.-Y. (1987). Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests Under Nonstandard Conditions., Journal of the American Statistical Association 82 605–610.
    Zentralblatt MATH: 0639.62020
    Digital Object Identifier: doi:10.1080/01621459.1987.10478472
  • [28] Shapiro, A. (1985). Asymptotic distribution of test statistics in the analysis of moment structures under inequality constraints., Biometrika 72 133–144.
    Zentralblatt MATH: 0596.62019
    Digital Object Identifier: doi:10.1093/biomet/72.1.133
  • [29] Silvapulle, M. J. and Sen, P. K. (2001)., Constrained Statistical Inference: Inequality, Order, and Shape Restrictions. Wiley.
    Zentralblatt MATH: 1077.62019
  • [30] Van der Vaart, A. W. (2000)., Asymptotic Statistics 3. Cambridge University Press.
    Zentralblatt MATH: 0910.62001
  • [31] Wakeley, J. (2009). Coalescent theory: an introduction., Roberts & Company.
    Zentralblatt MATH: 1366.92001
  • [32] Wilks, S. S. (1938). The large-sample distribution of the likelihood ratio for testing composite hypotheses., The Annals of Mathematical Statistics 9 60–62.
    Zentralblatt MATH: 0018.32003
    Digital Object Identifier: doi:10.1214/aoms/1177732360
    Project Euclid: euclid.aoms/1177732360

The Institute of Mathematical Statistics and the Bernoulli Society

Electronic Journal of Statistics

New content alerts

Email RSS ToC RSS Article
  • You have access to this content.
  • You have partial access to this content.
  • You do not have access to this content.
Turn Off MathJax

What is MathJax?

More like this

+ See more