Buradasınız

Anasayfa » Content

Open Problems on Connectivity of Fibers with Positive Margins in Multi-dimensional Contingency Tables

Journal Name:

  • Journal of Algebraic Statistics

Publication Year:

  • 2010

Key Words:

Author NameUniversity of Author

AMS Codes:

Abstract (2. Language): 
Diaconis-Sturmfels developed an algorithm for sampling from conditional distributions for a statistical model of discrete exponential families, based on the algebraic theory of toric ideals. This algorithm is applied to categorical data analysis through the notion of Markov bases. Initiated with its application to Markov chain Monte Carlo approach for testing statistical fitting of the given model, many researchers have extensively studied the structure of Markov bases for models in computational algebraic statistics. In the Markov chain Monte Carlo approach for testing statistical fitting of the given model, a Markov basis is a set of moves connecting all contingency tables satisfying the given margins. Despite the computational advances, there are applied problems where one may never be able to compute a Markov basis. In general, the number of elements in a minimal Markov basis for a model can be exponentially many. Thus, it is important to compute a reduced number of moves which connect all tables instead of computing a Markov basis. In some cases, such as logistic regression, positive margins are shown to allow a set of Markov connecting moves that are much simpler than the full Markov basis. Such a set is called a Markov subbasis with assumption of positive margins. In this paper we summarize some computations of and open problems on Markov subbases for contingency tables with assumption of positive margins under specific models as well as develop algebraic methods for studying connectivity of Markov moves with margin positivity to develop Markov sampling methods for exact conditional inference in statistical models where the Markov basis is hard to compute.
Bookmark/Search this post with
FULL TEXT (PDF): 
PDF icon arastirmax-open-problems-connectivity-fibers-positive-margins-multi-dimensional-contingency-tables.pdf
  • 1
13-26
  • English

REFERENCES

References: 

[1] 4ti2 Team. 4ti2 – a software package for algebraic, geometric and combinatorial
problems on linear spaces, 2006. Available at www.4ti2.de.
[2] S. Aoki and A. Takemura. Markov chain Monte Carlo exact tests for incomplete
two-way contingency table. Journal of Statistical Computation and Simulation, 75
(10):787–812, 2005.
[3] S. Aoki, A. Takemura, and R. Yoshida. Indispensable monomials of toric ideals and
markov bases. J of Symbolic Computations, 43:490–509, 2008.
[4] Y. M. M. Bishop, S. E. Fienberg, and P. W. Holland. Discrete Multivariate Analysis:
Theory and Practice. The MIT Press, Cambridge, Massachusetts, 1975.
[5] J. G. Booth and J. W. Butler. An importance sampling algorithm for exact conditional
tests in loglinear models. Biometrika, 86:321–332, 1999.
[6] F. Bunea and J. Besag. Mcmc in i×j ×k contingency tables. Monte Carlo Methods.
N. Madras ed. Communications, American Mathematical Society, pages 25–36, 2000.
[7] B. Caffo. exactloglintest: A program for monte carlo conditional
analysis of log-linear models, 2006. Available at
http://www.cran.r-project.org/src/contrib/Descriptions/exactLoglinTest.html.
REFERENCES 25
[8] Y. Chen, I. Dinwoodie, A. Dobra, and M. Huber. Lattice points, contingency tables,
and sampling. In Integer points in polyhedra—geometry, number theory, algebra, optimization,
volume 374 of Contemp. Math., pages 65–78. Amer. Math. Soc., Providence,
RI, 2005.
[9] Y. Chen, I. H. Dinwoodie, and S. Sullivant. Sequential importance sampling for
multiway tables. The Annals of Statistics, 34:523–545, 2006.
[10] Y. Chen, I. Dinwoodie, and R. Yoshida. Markov chains, quotient ideals, and connectivity
with positive margins. Algebraic and Geometric Methods in Statistics dedicated
to Professor Giovanni Pistone (P. Gibilisco, E. Riccomagno, M.-P. Rogantin, H. P.
Wynn, eds.), 2008. To appear.
[11] CoCoATeam. Cocoa: a system for doing computations in commutative algebra, 2007.
Available at http://cocoa.dima.unige.it.
[12] D. Cox, J. Little, and D. O’Shea. Ideals, Varieties, and Algorithms. Springer, New
York, 2nd edition edition, 1997.
[13] M. Cryan, M. Dyer, and D. Randall. Approximately counting integral flows and cellbounded
contingency tables. In Proc. STOC’05, pages 413–422, Baltimore, Maryland,
USA, May 2005.
[14] J. De Loera and S. Onn. Markov bases of three-way tables are arbitrarily complicated.
Journal of Symbolic Computation, 41:173–181, 2005.
[15] P. Diaconis and B. Sturmfels. Algebraic algorithms for sampling from conditional
distributions. Ann. Statist., 26(1):363–397, 1998. ISSN 0090-5364.
[16] P. Diaconis, D. Eisenbud, and B. Sturmfels. Lattice walks and primary decomposition.
In Mathematical essays in honor of Gian-Carlo Rota (Cambridge, MA, 1996), volume
161 of Progr. Math., pages 173–193. Birkh¨auser Boston, Boston, MA, 1998.
[17] M. Drton, B. Sturmfels, and S. Sullivant. Lectures on Algebraic Statistics. Springer,
New York, 2009. ISBN 978-3-7643-8904-8.
[18] R. A. Fisher. On the interpretation of 2 from contingency tables, and the calculation
of p. Journal of the Royal Statistical Society, 85(1):87–94, 1922.
[19] D. Geiger, C. Meek, and B. Sturmfels. On the toric algebra of graphical models. Ann.
Statist., 34(3):1463–1492, 2006.
[20] D. Grayson and M Stillman. Macaulay 2, a software system for research in algebraic
geometry, 2006. http://www.math.uiuc.edu/Macaulay2/.
[21] G.-M. Greuel, G. Pfister, and H. Schoenemann. Singular: A computer algebra system
for polynomial computations, 2006. http://www.singular.uni-kl.de.
REFERENCES 26
[22] S. W. Guo and E. A. Thompson. Performing the exact test of hardy-weinberg proportion
for multiple alleles. Biometrics, 48:361–372, 1992.
[23] S. J. Haberman. A warning on the use of chi-squared statistics with frequency tables
with small expected cell counts. J. Amer. Statist. Assoc., 83(402):555–560, 1988.
ISSN 0162-1459.
[24] H. Hara, A. Takemura, and R. Yoshida. On connectivity of fibers with positive
marginals in multiple logistic regression. J of Multivariate Analysis, 2009. In press.
[25] R. Hemmecke and P. Malkin. Computing generating sets of lattice ideals. Journal of
Symbolic Computation, 44(10):1463–1476, 2009.
[26] S. Hosten and S. Sullivant. Ideals of adjacent minors. Journal of Algebra, 277:615–642,
2004.
[27] M. Huber, Y. Chen, I. Dinwoodie, A. Dobra, and M. Nicholas. Monte carlo algorithms
for Hardy-Weinberg proportions. Biometrics, 62:49–53, 2006.
[28] M. Kreuzer and L. Robbiano. Computational Commutative Algebra. Springer, New
York, 2000.
[29] F. Rapallo. Markov bases and structural zeros. Journal of Symbolic Computation,
41:164–172, 2006.
[30] F. Rapallo and M. P. Rogantin. Markov chains on the reference set of contingency
tables with upper bounds. Metron, 65(1), 2007.
[31] F. Rapallo and R. Yoshida. Markov bases and subbases for bounded contingency
tables. Annals of Institution of Statistical Mathematics, 2010. In press. Available at
arxiv:0905.4841.
[32] J. Shao. Mathematical Statistics. Springer Verlag, New York, 1998.
[33] B. Sturmfels. Gr¨obner Bases and Convex Polytopes, volume 8 of University Lecture
Series. American Mathematical Society, Providence, RI, 1996. ISBN 0-8218-0487-1.
[34] A. Takemura and S. Aoki. Distance reducing Markov bases for sampling from a
discrete sample space. Bernoulli, 11(5):793–813, 2005.
[35] R Development Core Team. R: A language and environment for statistical computing,
2004. http://www.R-project.org.

Thank you for copying data from http://www.arastirmax.com