Applying linear time-varying constraints to econometric models: With an application to demand systems

When linear equality constraints are invariant through time they can be incorporated into estimation by restricted least squares. If, however, the constraints are time-varying, this standard methodology cannot be applied. In this paper we show how to incorporate linear time-varying constraints into the estimation of econometric models. The method involves the augmentation of the observation equation of a state-space model prior to estimation by the Kalman filter. Numerical optimisation routines are used for the estimation. A simple example drawn from demand analysis is used to illustrate the method and its application.

Twisted quantum affine superalgebra U-q[sl(2/2)((2))], U-q[osp(2/2)] invariant R-matrices and a new integrable electronic model

We describe the twisted affine superalgebra sl(2\2)((2)) and its quantized version U-q[sl(2\2)((2))]. We investigate the tensor product representation of the four-dimensional grade star representation for the fixed-point sub superalgebra U-q[osp(2\2)]. We work out the tensor product decomposition explicitly and find that the decomposition is not completely reducible. Associated with this four-dimensional grade star representation we derive two U-q[osp(2\2)] invariant R-matrices: one of them corresponds to U-q [sl(2\2)(2)] and the other to U-q [osp(2\2)((1))]. Using the R-matrix for U-q[sl(2\2)((2))], we construct a new U-q[osp(2\2)] invariant strongly correlated electronic model, which is integrable in one dimension. Interestingly this model reduces in the q = 1 limit, to the one proposed by Essler et al which has a larger sl(2\2) symmetry.

Nmr imaging of the diffusion of water into poly(tetrahydrofurfuryl methacrylate-co-hydroxyethyl methacrylate)

0Nuclear magnetic resonance (n.m.r.) imaging was used to study the ingress of water into poly(tetrahydrofurfuryl methacrylate-co-hydroxyethyl methacrylate). The study offers strong evidence that the diffusion is Fickian in nature. The diffusion coefficient, D, obtained by fitting the underlying diffusion profile, attainable from the images, according to the equation for Fickian diffusion, is 1.5 x 10(-11) m(2) s(-1), which is in good correlation with the value of 2.1 x 10(-11) m(2) s(-1), obtained from mass uptake measurements. Additionally, from the T-2-weighted images, Superimposed features observed in addition to the underlying Fickian diffusion profiles were shown to have a longer spin-spin relaxation time, T-2. This Suggests the presence of two types of water within the polymer matrix; a less mobile phase of absorbed water that is interacting strongly with the polymer matrix and a more mobile phase of absorbed water residing within the cracks observed in the environmental scanning electron micrograph. (C) 1997 Elsevier Science Ltd.