Akimichi Takemura

Some characterizations of minimal Markov basis for sampling from discrete conditional distributions

In this paper we given some basic characterizations of minimal Markov basis for a connected Markov chain, which is used for performing exact tests in discrete exponential families given a sufficient statistic. We also give a necessary and sufficient condition for uniqueness of minimal Markov basis. A general algebraic algorithm for constructing a connected Markov chain was given by Diaconis and Sturmfels (1998,The Annals of Statistics,26, 363–397). Their algorithm is based on computing Gröbner basis for a certain ideal in a polynomial ring, which can be carried out by using available computer algebra packages. However structure and interpretation of Gröbner basis produced by the packages are sometimes not clear, due to the lack of symmetry and minimality in Gröbner basis computation. Our approach clarifies partially ordered structure of minimal Markov basis.

Markov chain Monte Carlo exact tests for incomplete two-way contingency tables

We consider testing the quasi-independence hypothesis for two-way contingency tables which contain some structural zero cells. For sparse contingency tables where the large sample approximation is not adequate, the Markov chain Monte Carlo exact tests are powerful tools. To construct a connected chain over the two-way contingency tables with fixed sufficient statistics and an arbitrary configuration of structural zero cells, an algebraic algorithm proposed by Diaconis and Sturmfels [Diaconis, P. and Sturmfels, B. (1998). The Annals of statistics, 26, pp. 363–397.] can be used. However, their algorithm does not seem to be a satisfactory answer, because the Markov basis produced by the algorithm often contains many redundant elements and is hard to interpret. We derive an explicit characterization of a minimal Markov basis, prove its uniqueness, and present an algorithm for obtaining the unique minimal basis. A computational example and the discussion on further basis reduction for the case of positive sufficient statistics are also given.

Tensor Analysis of ANOVA Decomposition

Abstract The analogy between ANOVA for general n-factor crossed layouts and the ANOVA-type decomposition of square integrable statistics is demonstrated using the notions and notations of tensor analysis and multilinear algebra. A theory of tensors is developed in such a way that (a) it can be immediately applied in computer programs, and (b) it can be easily generalized to L 2 spaces.

Empirical characteristic function approach to goodness-of-fit tests for the Cauchy distribution with parameters estimated by MLE or EISE

We consider goodness-of-fit tests of the Cauchy distribution based on weighted integrals of the squared distance between the empirical characteristic function of the standardized data and the characteristic function of the standard Cauchy distribution. For standardization of data Gürtler and Henze (2000,Annals of the Institute of Statistical Mathematics,52, 267–286) used the median and the interquartile range. In this paper we use the maximum likelihood estimator (MLE) and an equivariant integrated squared error estimator (EISE), which minimizes the weighted integral. We derive an explicit form of the asymptotic covariance function of the characteristic function process with parameters estimated by the MLE or the EISE. The eigenvalues of the covariance function are numerically evaluated and the asymptotic distributions of the test statistics are obtained by the residue theorem. A simulation study shows that the proposed tests compare well to tests proposed by Gürtler and Henze and more traditional tests based on the empirical distribution function.

Holonomic gradient descent and its application to the Fisher-Bingham integral

We give a new algorithm to find local maximum and minimum of a holonomic function and apply it for the Fisher-Bingham integral on the sphere

On connectivity of fibers with positive marginals in multiple logistic regression

S^n

Inadmissability of non-order-preserving orthogonally invariant estimators of the covariance matrix in the case of Stein's loss

, which is used in the directional statistics. The method utilizes the theory and algorithms of holonomic systems.

Indispensable monomials of toric ideals and Markov bases

In this paper we consider exact tests of a multiple logistic regression with categorical covariates via Markov bases. In many applications of multiple logistic regression, the sample size is positive for each combination of levels of the covariates. In this case we do not need a whole Markov basis, which guarantees connectivity of all fibers. We first give an explicit Markov basis for multiple Poisson regression. By the Lawrence lifting of this basis, in the case of bivariate logistic regression, we show a simple subset of the Markov basis which connects all fibers with a positive sample size for each combination of levels of covariates.

Goodness-of-fit tests for symmetric stable distributions—Empirical characteristic function approach

For orthogonally invariant estimation of [Sigma] of Wishart distribution using Steins loss, any estimator which does not preserve the order of the sample eigenvalues is dominated by a modified estimator preserving the order.

On a simple strategy weakly forcing the strong law of large numbers in the bounded forecasting game

Extending the notion of indispensable binomials of a toric ideal [Takemura, Akimichi, Aoki, Satoshi, 2004. Some characterizations of minimal Markov basis for sampling from discrete conditional distributions. Ann. Inst. Statist. Math. 56 (1), 1-17; Ohsugi, Hidefumi, Hibi, Takayuki, 2005. Indispensable binomials of finite graphs. J. Algebra Appl. 4 (4), 421-434], we define indispensable monomials of a toric ideal and establish some of their properties. They are useful for searching indispensable binomials of a toric ideal and for proving the existence or non-existence of a unique minimal system of binomial generators of a toric ideal. Some examples of indispensable monomials from statistical models for contingency tables are given.