Asymptotic properties of computationally efficient alternative estimators for a class of multivariate normal models

Parameters of Gaussian multivariate models are often estimated using the maximum likelihood approach. In spite of its merits, this methodology is not practical when the sample size is very large, as, for example, in the case of massive georeferenced data sets. In this paper, we study the asymptotic properties of the estimators that minimize three alternatives to the likelihood function, designed to increase the computational efficiency. This is achieved by applying the information sandwich technique to expansions of the pseudo-likelihood functions as quadratic forms of independent normal random variables. Theoretical calculations are given for a first-order autoregressive time series and then extended to a two-dimensional autoregressive process on a lattice. We compare the efficiency of the three estimators to that of the maximum likelihood estimator as well as among themselves, using numerical calculations of the theoretical results and simulations.     

Dihalodimethyltin(IV) complexes of 2‐(pyrazol‐1‐ylmethyl)pyridine

Reaction of dichloro‐ and dibromodimethyltin(IV) with 2‐(pyrazol‐1‐ylmethyl)pyridine (PMP) afforded [SnMe₂Cl₂(PMP)] and [SnMe₂Br₂(PMP)] respectively. The new complexes were characterized by elemental analysis and mass spectrometry and by IR, Raman and NMR (¹H, ¹³C) spectroscopies. Structural studies by X‐ray diffraction techniques show that the compounds consist of discrete units with the tin atom octahedrally coordinated to the carbon atoms of the two methyl groups in a trans disposition (Sn? C = 2.097(5), 2.120(5) Å and 2.110(6), 2.121(6) Å in the chloro and in the bromo compounds respectively), two cis halogen atoms (Sn? Cl = 2.4908(16), 2.5447(17) Å; Sn? Br = 2.6875(11), 2.7464(9) Å) and the two donor atoms of the ligand (Sn? N = 2.407(4), 2.471(4) Å and 2.360(5), 2.455(5) Å). In both cases, the Sn? N(pyridine) bond length is markedly longer than the Sn? N(pyrazole) distance. Copyright © 2003 John Wiley & Sons, Ltd.     

CAS based approach for discussing subset construction

This paper continues the discussion of teaching nondeterminism (see [6]) where we presented a didactic approach introducing the notion of nondeterministic automata. Although in this paper we use the same methodology we have to face up to new didactic challenges. Namely, teaching the subset construction requires answers to the question how can CAS be used in teaching the different phases of mathematical problem solving so that we can reach higher cognitive efficiency.     

[VS_4Cu_6(Py)_8I_3]的合成和晶体结构

在(NH4)3VS4/CuI/Py反应体系中合成了新化合物 [VS4Cu6(Py)8I3]并测定其晶体结构。该化合物(C40H40N8Cu6I3S4V)属正交晶系, 空间群为Fdd2, 晶胞参数为: a = 29.924(6), b = 13.475(3), c = 25.853(5) , V = 10425(4) ?, Dc = 2.006 g/cm3, Mr = 1573.92, Z = 8, (MoK) = 4.546 mm-1, F(000) = 6048。结构由直接法解出, 用全矩阵最小二乘法修正, 最终偏离因子R = 0.023, wR = 0.069。簇合物分子是由6个带端基配体的Cu沿着四面体单元VS4的6条SS边配位而成, 6个Cu排列成了1个八面体, V基本位于八面体的中心, 整个分子具有C2对称性。     

Shape preservation regions for six-dimensional spaces

We analyze the critical length for design purposes of six-dimensional spaces invariant under translations and reflections containing the functions 1, cos t and sin t. These spaces also contain the first degree polynomials as well as trigonometric and/or hyperbolic functions. We identify the spaces whose critical length for design purposes is greater than 2π and find its maximum 4π. By a change of variables, two biparametric families of spaces arise. We call shape preservation region to the set of admissible parameters in order that the space has shape preserving representations for curves. We describe the shape preserving regions for both families. To our friend Mariano Gasca on occasion of his 60th birthday Research partially supported by the Spanish Research Grant MTM2006-03388, by Gobierno de Aragón and Fondo Social Europeo.     

Remarks on a theorem of Taskinen on spaces of continuous functions

We clarify and prove in a simpler way a result of Taskinen about symmetric operators on C(Kⁿ), K an uncountable metrizable compact space. To do this we prove that, for any compact space K and any n ∈ ?, the symmetric injective n–tensor product of C(K), , is complemented in C(B_C(K)*), a result of independent interest. The techniques we develop allow us to extend the result in several directions. We also show that the hypothesis of metrizability and uncountability cannot be removed.     

Inferring mixed-culture growth from total biomass data in a wavelet approach

It is shown that the presence of mixed-culture growth in batch fermentation processes can be very accurately inferred from total biomass data by means of the wavelet analysis for singularity detection. This is accomplished by considering simple phenomenological models for the mixed growth and the more complicated case of mixed growth on a mixture of substrates. The main quantity provided by the wavelet analysis is the Hölder exponent of the singularity that we determine for our illustrative examples. The numerical results point to the possibility that Hölder exponents can be used to characterize the nature of the mixed-culture growth in batch fermentation processes with potential industrial applications. Moreover, the analysis of the same data affected by the common additive Gaussian noise still lead to the wavelet detection of the singularities although the Hölder exponent is no longer a useful parameter.     

Air-activated carbons from almond tree pruning: Preparation and characterization

In this work the results obtained in the preparation and characterization of carbons made from almond tree pruning by non-catalytic and catalytic gasification (using K and Co) with air are analyzed and discussed. The main aim was to obtain high quality activated carbons at the lowest possible cost. The variables studied have been the temperature (190-260 °C) and the time (1-10 h) in non-catalytic gasification and the influence of the catalyst type (K and Co, 1 wt.% referred to cation, at 190 °C and 1 h) and the time (1-4 h) in catalytic gasification with Co at 190 °C. The air flow rate used in all the series was 167 cm³ min⁻¹. In non-catalytic gasification the reaction normalized rate versus the conversion degree was maintained until a conversion value of 10% for the experiment made at 260 °C since, at lower temperatures, this rate drops quickly for low conversion values. The N₂ adsorption isotherms for the carbons of this series resemble type I, although there is an increase of N₂ adsorbed volume at relatively high pressures. A temperature rise produced an increase of the carbon porosity and BET specific surface (116-469 m² g⁻¹). The activation time has a positive effect on the N₂ volume adsorbed by the carbons. The isotherms shapes were similar to those previously commented. A concentration equal to 1 wt.% was used to study the influence of the catalyst type. Under the studied experimental conditions, Co drives to a bigger porosity development than K, although with both catalysts a very similar pore size distribution is obtained. The activation time, in the gasifications catalyzed with Co, gives rise to a very important porosity development in the carbons. This produces a strong increase of the carbon specific surface area with very high values in the 4 h experiment, in which a BET specific surface of 959 m² g⁻¹ was obtained.