Bayesian Prediction Analysis for Growth Curve Model Using Noninformative Priors

We apply a Bayesian approach to the problem of prediction in an unbalanced growth curve model using noninformative priors. Due to the complexity of the model, no analytic forms of the predictive densities are available. We propose both approximations and a prediction-oriented Metropolis-Hastings sampling algorithm for two types of prediction, namely the prediction of future observations for a new subject and the prediction of future values for a partially observed subject. They are illustrated and compared through real data and simulation studies. Two of the approximations compare favorably with the approximation in Fearn (1975, Biometrika, 62, 89–100) and are very comparable to the more accurate Rao-Blackwellization from Metropolis-Hastings sampling algorithm.     

Single chain force spectroscopy - Reading the sequence of HP protein models

We study the elastic properties of single A/B random copolymer chains, with a specific sequence and use them as theoretical model for so called HP proteins. HP proteins carry hydrophilic (P) and hydrophobic (H) monomers. We predict a rich structure in the force-extension relations which can be attributed to the information in the sequence. The variational method is used to probe local minima on the path of stretching and releasing for the chain molecules. At a given force, we find multiple configurations which are separated by energy barriers. A collapsed globular configuration consists of several domains which unravel cooperatively. Upon stretching, the unfolding path shows a stepwise pattern corresponding to the unfolding of each domain. While releasing, several cores can be created simultaneously in the middle of the chain, resulting in a different path of collapse. The long-range interactions and stiffness of the chain simplify the potential landscape given by the disorder in sequence. Received 5 March 2002 / Received in final form 16 May 2002 Published online 13 August 2002     

提前还贷及其隐含期权的分析

可提前还款的定期贷款是隐含着期权的利率衍生物，本文建立CIR利率模型下可提前还款的定期贷款的数学模型，通过离散偏微分方程，建立了模型的计算方法，讨论了随机利率对提前还贷的影响．     

Constructions of External Difference Families and Disjoint Difference Families

External difference families (EDFs) are a type of new combinatorial designs originated from cryptography. In this paper, some earlier ideas of recursive and cyclotomic constructions of combinatorial designs are extended, and a number of classes of EDFs and disjoint difference families are presented. A link between a subclass of EDFs and a special type of (almost) difference sets is set up.     

Fabrication of patterned gold electrodes with spin-coated-and-fired Au(1 1 1) film by the soft lithography

We prepared high quality Au(1 1 1) film on Si wafer through the spin coating and thermal decomposition of a gold ink, spin-coated-and-fired (SCAF) Au film. The X-ray measurements, XRD and pole-figure analysis, showed that the SCAF Au film has a (1 1 1) out-of-plane orientation with a random in-plane orientation. In order to confirm the chemical activity of the SCAF Au film, we demonstrate the formation of patterned structures with the film by using soft lithography technique. The chemical activities of this physically stable SCAF Au film to the alkanethiols were at least equivalent those of physically deposited the Au films. The possibility of the mass production of micro patterned structure with the SCAF Au film was also demonstrated over the wide region on Si wafer by the microcontact lithography. These suggest that the Au film will help the easy fabrication of various nanosized devices on Si wafer and other substrates.     

An efficient construction of period-2 bulbs in the cubic Mandelbrot set with parametric boundaries

A parametric boundary equation is established for the principal period-2 bulb in the cubic Mandelbrot set. Using its geometry, an efficient escape-time algorithm which reduces the construction time for the period-2 bulbs in the cubic Mandelbrot set is introduced and the implementation graphic results display the fascinating fractal beauty     

Biphotonic recording effect of polarization gratings based on dye-doped liquid crystal films

This study investigates a holographic recording effect of biphotonic polarization gratings (BPGs) written on dye-doped liquid crystal (DDLC) films. One linearly polarized green light (λ_G = 514.5 nm) and a polarization-modulated interference pattern formed by two mutually coherent orthogonal (±45° with respect to the polarization of the green light) polarized red lights simultaneously excite the DDLC films to generate a BPG. The formation of BPGs depends primarily on the dichroism of the dye molecules and a sequence of mechanisms: photoisomerization, anisotropic adsorption and inhibition of dye adsorption. The cis-isomer absorbance-modulated distribution associated with the red polarization-modulation pattern induces the dye adsorption-modulated pattern, in turn, yielding the permanent BPG which generates a modulated twisted nematic (TN) structure pattern in the sample. It is found that each BPG is verified to be electrically switchable and thermally erasable. The switching time is in the order of milliseconds. Additionally, the recording time to form a BPG decreases with increasing intensity of the green pump beam.     

Bimodal fission in binary and ternary spontaneous fission of 252Cf

The hot bimodal fission of ²⁵²Cf is reexamined with new high-statistics data. We constructed a γ-γ-γ coincidence cube for binary fission and LCP-gated γ-γ matrix for ternary fission. By identifying the secondary fission fragments from their γ-ray transitions, we measured the yields for various fission splits. The normal neutron yield distribution is found to be Gaussian for Xe-Ru. However, the binary fission split of Ba-Mo is found to exhibit a bimodal neutron distribution with the “hot mode” corresponding to ≈3.1% of the total yield. In α ternary fission, the first measurements of yields for specific fission splits are presented. The Te-α-Ru and Xe-α-Mo neutron yields fit well with a single mode, but the Ba-α-Zr split shows evidence for an enhanced hot mode with an intensity of ≈13.8% of the normal mode. The text was submitted by the authors in English.     

A note on model diagnostics in longitudinal data analysis

Longitudinal study has become one of the most commonly adopted designs in medical research. The generalized estimating equations (GEE) method and/or mixed effects models are employed very often in causal inferences. The related model diagnostic procedures are not yet fully formalized, and perhaps never will be. The potential causes of major problems are the high variety of the dependence within subjects and/or the number of repeated measurements. A single testing procedure, e.g., run test, is not possible to resolve all model diagnostics problems in longitudinal data analysis. Multiple quantitative indexes for model diagnostics are needed to take into account this variety. We propose eight testing procedures for randomness accompanied with some conventional and/or non-conventional plots to remedy model diagnostics in longitudinal data analysis. The proposed issue in this paper is well illustrated with four clinical studies in Taiwan.