Previous |  Up |  Next

Article

Keywords:
conditional independence; Markov basis; closure of exponential family; permutation; L-decomposable
Summary:
The L-decomposable and the bi-decomposable models are two families of distributions on the set $S_n$ of all permutations of the first $n$ positive integers. Both of these models are characterized by collections of conditional independence relations. We first compute a Markov basis for the L-decomposable model, then give partial results about the Markov basis of the bi-decomposable model. Using these Markov bases, we show that not all bi-decomposable distributions can be approximated arbitrarily well by strictly positive bi-decomposable distributions.
References:
[1] D. Cox, J. Little, and D. O’Shea: Ideals, Varieties, and Algorithms. Springer, New York 1992. MR 1189133
[2] D. E. Critchlow, M. A. Fligner, and J. S. Verducci: Probability models on rankings. J. Math. Psych. 35 (1991), 294–318. MR 1128236
[3] V. Csiszár: Conditional independence relations and log-linear models for random matchings. Acta Math. Hungar. (2008), Online First. MR 2487466
[4] P. Diaconis and N. Eriksson: Markov bases for noncommutative Fourier analysis of ranked data. J. Symbolic Comput. 41 (2006), 173–181. MR 2197153
[5] P. Diaconis and B. Sturmfels: Algebraic algorithms for sampling from conditional distributions. Ann. Statist. 26 (1998), 363–397. MR 1608156
[6] A. Dobra: Markov bases for decomposable graphical models. Bernoulli 9 (2003), 1093–1108. MR 2046819 | Zbl 1053.62072
[7] M. A. Fligner and J. S. Verducci (eds.): Probability Models and Statistical Analyses for Ranking Data. Springer, New York 1993. MR 1237197
[8] 4ti2 team: 4ti2 – A software package for algebraic, geometric and combinatorial problems on linear spaces. Available at www.4ti2.de.
[9] D. Geiger, C. Meek, and B. Sturmfels: On the toric algebra of graphical models. Ann. Statist. 34 (2006), 1463–1492. MR 2278364
[10] R. D. Luce: Individual Choice Behavior. Wiley, New York 1959. MR 0108411 | Zbl 0093.31708
[11] J. I. Marden: Analyzing and Modelling Rank Data. Chapman and Hall, London 1995. MR 1346107
[12] G. Pistone, E. Riccomagno, and H. P. Wynn: Algebraic Statistics. Chapman and Hall/CRC, Bocan Raton 2000. MR 2332740
[13] F. Rapallo: Toric statistical models: parametric and binomial representations. Ann. Inst. Statist. Math. 59 (2007), 727–740. MR 2397736 | Zbl 1133.62343
[14] B. Sturmfels: Gröbner bases and convex polytopes. Amer. Math. Soc., Providence RI 1996. MR 1363949 | Zbl 0856.13020
[15] S. Sullivant: Toric Ideals in Algebraic Statistics. Ph.D. Thesis, University of California, Berkeley 2005. MR 2623019
[16] A. Takemura and S. Aoki: Some characterizations of minimal Markov basis for sampling from discrete conditional distributions. Ann. Inst. Statist. Math. 56 (2004), 1–17. MR 2053726
Partner of
EuDML logo