On the Estimation of Integrated Covariance Functions of Stationary Random Fields

Abstract.  For stationary vector-valued random fields on     the asymptotic covariance matrix for estimators of the mean vector can be given by integrated covariance functions. To construct asymptotic confidence intervals and significance tests for the mean vector, non-parametric estimators of these integrated covariance functions are required. Integrability conditions are derived under which the estimators of the covariance matrix are mean-square consistent. For random fields induced by stationary Boolean models with convex grains, these conditions are expressed by sufficient assumptions on the grain distribution. Performance issues are discussed by means of numerical examples for Gaussian random fields and the intrinsic volume densities of planar Boolean models with uniformly bounded grains.     

Exact null distributions of quadratic distribution-free statistics for two-way classification

We present new techniques for computing exact distributions of ‘Friedman-type’ statistics. Representing the null distribution by a generating function allows for the use of general, not necessarily integer-valued rank scores. Moreover, we use symmetry properties of the multivariate generating function to accelerate computations. The methods also work for cases with ties and for permutation statistics. We discuss some applications: the classical Friedman rank test, the normal scores test, the Friedman permutation test, the Cochran–Cox test and the Kepner–Robinson test. Finally, we shortly discuss self-made software for computing exact p-values.     

THE non-null distribution of the likelihood ratio criterion for testing the hypothesis that the covariance matrix is diagonal

This article deals with the exact non-null distribution of the likelihood ratio criterion for testing the hypothesis that the covariance matrix in a multinormal distribution is diagonal. The exact non-null moments as well as the exact non-null distribution are derived. The distribution is also expressed in computable form with the help of inverse Mellin transform and calculus of residues. The results obtained in this article are useful in studying the power of testing several correlation coefficients simultaneously.     

Exponential random graph models for little networks

Statistical models for social networks have enabled researchers to study complex social phenomena that give rise to observed patterns of relationships among social actors and to gain a rich understanding of the interdependent nature of social ties and actors. Much of this research has focused on social networks within medium to large social groups. To date, these advances in statistical models for social networks, and in particular, of Exponential-Family Random Graph Models (ERGMS), have rarely been applied to the study of small networks, despite small network data in teams, families, and personal networks being common in many fields. In this paper, we revisit the estimation of ERGMs for small networks and propose using exhaustive enumeration when possible. We developed an R package that implements the estimation of pooled ERGMs for small networks using Maximum Likelihood Estimation (MLE), called “ergmito”. Based on the results of an extensive simulation study to assess the properties of the MLE estimator, we conclude that there are several benefits of direct MLE estimation compared to approximate methods and that this creates opportunities for valuable methodological innovations that can be applied to modeling social networks with ERGMs.     

A statistical software procedure for exact parametric and nonparametric likelihood-ratio tests for two-sample comparisons

Two-sample comparisons belonging to basic class of statistical inference are extensively applied in practice. There is a rich statistical literature regarding different parametric methods to address these problems. In this context, most of the powerful techniques are assumed to be based on normally distributed populations. In practice, the alternative distributions of compared samples are commonly unknown. In this case, one can propose a combined test based on the following decision rules: (a) the likelihood-ratio test (LRT) for equality of two normal populations and (b) the Shapiro–Wilk (S-W) test for normality. The rules (a) and (b) can be merged by, e.g., using the Bonferroni correction technique to offer the correct comparison of the samples distribution. Alternatively, we propose the exact density-based empirical likelihood (DBEL) ratio test. We develop the tsc package as the first R package available to perform the two-sample comparisons using the exact test procedures: the LRT; the LRT combined with the S-W test; as well as the newly developed DBEL ratio test. We demonstrate Monte Carlo (MC) results and a real data example to show an efficiency and excellent applicability of the developed procedure.     

Accurate probabilities for the sign test

Limitations in currently available methods for producing significance probabilities for the sign test are discussed. Two simple modifications to the continuity corrected normal approximation are derived and presented in a simple form. These modifications are shown to markedly reduce the relative error in approximating exact probabilities. The relative simplicity of these modifications and the importance of accurate p values suggest that one or both modifications could be useful improvements.     

Properties of a One-Sided Likelihood Ratio Test as Applied to Pool Screening

In the control of tropical disease, data are typically collected using pool screening design. When eradication programs have been in place for a period of time, researchers are interested in testing whether the disease prevalence is below a certain target level using one-sided likelihood ratio test (LRT). We will investigate the finite and large-sample properties of this test statistic. Based on simulations, if the number of pools is not large enough, the LRT has inflated type I error rate. Consequently, researchers will make the critical mistake of stopping the treatment when the target level has not been reached.     

On the effect of overdispersion on exact conditional tests

Let Y ₁, . . ., Y_n denote independent random variables such that Y_j has a one-parameter exponential family distribution with canonical parameter θ _j =λ+ψ X_j ; here X ₁, . . ., X_n are known constants. Consider a test of the null hypothesis ψ=0. Under the null hypothesis, A =Σ Y_j is sufficient for λ and, hence, a test of ψ=0 may be based on the conditional distribution of T =Σ X_j Y_j given A , which is independent of λ. In this paper, the effects of overdispersion due to a mixture model on the conditional distribution of T given A are considered.     

Multiplicative algorithms for computing optimum designs

We study a new approach to determine optimal designs, exact or approximate, both for the uncorrelated case and when the responses may be correlated. A simple version of this method is based on transforming design points on a finite interval to proportions of the interval. Methods for determining optimal design weights can therefore be used to determine optimal values of these proportions. We explore the potential of this method in a range of examples encompassing linear and non-linear models, some assuming a correlation structure and some with more than one design variable.     

On asymptotics of multivariate integrals with applications to records

Let { X _n ,n≥1} be a sequence of iid. Gaussian random vectors in R ^d , d≥2, with nonsingular distribution function F. In this paper the asymptotics for the sequence of integrals I _F,n (G _n )?n∫ _{R ^d} G _n ^n?1( X ) dF( X ) is considered with G _n some distribution function on R ^d . In the case G _n =F the integral I _F,n (F)/n is the probability that a record occurs in X ₁,…, X _n at index n. [1] Gnedin, A.V. 1998. Records from a Multivariate Normal Sample. Statist. Probab. Lett., 39: 11–15. [Crossref], [Web of Science ®] , [Google Scholar] obtained lower and upper asymptotic bounds for this case, whereas [2] Ledford, W.A. and Twan, A.J. 1998. On the Tail Concomitant Behaviour for Extremes. Adv. Appl. Probab., 30: 197–215. [Crossref], [Web of Science ®] , [Google Scholar] showed the rate of convergence if d=2. In this paper we derive the exact rate of convergence of I _F,n (G _n ) for d≥2 under some restrictions on the distribution function G _n . Some related results for multivariate Gaussian tails are discussed also.