A resampling approach for adjustment in prediction models for covariate measurement error

Recent works on covariate measurement errors focus on the possible biases in model coefficient estimates. Usually, measurement error in a covariate tends to attenuate the coefficient estimate for the covariate, i.e., a bias toward the null occurs. Measurement error in another confounding or interacting variable typically results in incomplete adjustment for that variable. Hence, the coefficient for the covariate of interest may be biased either toward or away from the null. This paper presents a new method based on a resampling technique to deal with covariate measurement errors in the context of prediction modeling. Prediction accuracy is our primary parameter of interest. Prediction accuracy of a model is defined as the success rate of prediction when the model predicts new response. We call our method bootstrap regression calibration (BRC). We study logistic regression with interacting covariates as our prediction model. We measure the prediction accuracy of a model by receiver operating characteristic (ROC) method. Results from simulations show that bootstrap regression calibration offers consistent enhancement over the commonly used regression calibration (RC) method in terms of improving prediction accuracy of the model and reducing bias in the estimated coefficients.     

Surface and printing properties of synthetic film papers

We studied the surfaces, including both the composition effects and the processing rates, of polypropylene (PP) composite films used for synthetic paper to determine the surface free energy (γ_s) and the irregularities on the film surfaces. We correlated these two characteristics to the printing quality by assessing the facility with which the offset ink was removed from the surface of the paper and also the ink absorption. Five films with different compositions were uniaxially oriented with a flat‐die extruder at two different stretching rates. The results of scanning electron microscopy (SEM) of the films showed good dispersion and distribution of the filler particles used in the compositions of the films and also of the polystyrene (PS) dispersed throughout the PP matrix. The SEM analysis also revealed slightly high surface irregularities on the film surfaces through a high concentration of CaCO₃, which thus increased the coefficients of static and kinetic friction and the γ_s values. These film properties created better printing quality and also more strongly fixed offset ink onto the film. However, the films with high relative quantities of PS in their composition showed a high polar component in their total γ_s when compared to films with less PS or no PS in their compositions. However, because of the apolar characteristic of the offset printing ink, the ink absorption worsened. The films underwent stretching at two different rates, which did not significantly affect the γ_s values or the friction coefficients; however, they did slightly change the printing quality and ink adhesion. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 88: 2346–2355, 2003     

Use of OSWALD for analyzing longitudinal data with informative dropout

OSWALD (Object-oriented Software for the Analysis of Longitudinal Data) is flexible and powerful software written for S-PLUS for the analysis of longitudinal data with dropout for which there is little other software available in the public domain. The implementation of OSWALD is described through analysis of a psychiatric clinical trial that compares antidepressant effects in an elderly depressed sample and a simulation study. In the simulation study, three different dropout mechanisms: completely random dropout (CRD), random dropout (RD) and informative dropout (ID), are considered and the results from using OSWALD are compared across mechanisms. The parameter estimates for ID-simulated data show less bias with OSWALD under the ID missing data assumption than under the CRD or RD assumptions. Under an ID mechanism, OSWALD does not provide standard error estimates. We supplement OSWALD with a bootstrap procedure to derive the standard errors. This report illustrates the usage of OSWALD for analyzing longitudinal data with dropouts and how to draw appropriate conclusions based on the analytic results under different assumptions regarding the dropout mechanism.     

Morphological influence on mechanical characterization of ethylene‐vinyl acetate copolymer–clay nanocomposites

Ethylene‐vinyl acetate copolymer (EVA)/montmorillonite (MMT) clay nanocomposites with varying degree of intercalation and exfoliation have been prepared using direct melt blending techniques with various degrees of polarity (9, 18, and 28 wt% vinyl acetate [VA]) and two different types of clay modification. Morphological characterization using wide‐angle X‐ray scattering (WAXS) and transmission electron microscopy (TEM) have indicated/confirmed the presence of intercalation and/or a combination of intercalation and exfoliation existing in the nanocomposites. The effects of these (simple intercalation or mixed intercalation/exfoliation) states and the effect of changing matrix polarity (by changing VA wt% content) on the nanocomposite mechanical behavior were studied. There is sufficient evidence from the mechanical studies that 1) the presence of nanoclay can simultaneously improve modulus and strength of the nanocomposites, and 2) the mechanical properties are a combined function of the clay concentration and the nanocomposite morphology (due to the VA wt% and presence of clay). It is shown here that interrelation between the VA wt% content and the clay exfoliation affects the mechanical properties in a way that has a positive and increasing slope with increasing loading of clay. It is shown that a clear understanding of the nanocomposite mechanical properties can be obtained from its morphological analysis. POLYM. ENG. SCI., 45:889–897, 2005. © 2005 Society of Plastics Engineers     

Rheology and Physical Characteristics of Synthetic Biodegradable Aliphatic Polymer Blends Dispersed with MWNTs

PLA/PBAT blends and PLA/PBAT/MWNT nanocomposite systems were prepared via a melt mixing process to examine their thermal and rheological properties. To compare the polymer blend/MWNT nanocomposite with a pure polymer/MWNT nanocomposite, PLA/MWNT, PBAT/MWNT, and PLA/PBAT/MWNT nanocomposite systems were prepared. TEM and SEM were used to observe that one phase has better affinity with the MWNT, while the MWNT was found to increase both the thermal properties of the PLA/PBAT blends and rheological properties of the PLA/PBAT/MWNT nanocomposite with distinct shear‐thinning behavior due to the addition of the MWNT. An increase in the storage (G′) and loss (G″) moduli for the PLA/PBT/MWNT nanocomposite was also observed.

     

Structural,magnetic, vibrational and impedance properties of Pr and Ti codoped BiFeO3 multiferroic ceramics

Single-phase (Bi_1−xPr_x)(Fe_1−xTi_x)O₃ ceramics (x=0.03, 0.06, and 0.10 as BPFT-3, BPFT-6 and BPFT-10, respectively) were synthesized by conventional solid state reaction method. The effect of varying Pr and Ti codoping concentration on the structural, magnetic, dielectric and optical properties of the BPFT ceramics have been investigated. X-ray diffraction indicated pure rhombohedral phase formation for BPFT-3 and BPFT-6 ceramics, however, a structural phase transition from a rhombohedral to an orthorhombic phase has been observed for BPFT-10 ceramic. The maximum remnant magnetization of 0.1824 emu/g has been observed in BPFT-6. With increasing codoping concentration the room temperature dielectric measurements showed enhancement in dielectric properties with reduced dielectric loss. UV–vis diffuse reflectance spectra demonstrated the strong absorption of light in the visible region for a band gap variation 2.31–2.34 eV. Infrared spectroscopy indicated the shifting of Bi/Pr–O and Fe/Ti–O bonds vibrations and change in Fe/Ti–O bond lengths. Decrease in the conductivity on increasing Pr and Ti concentration in BFO is attributed to an enhancement in the barrier properties leading to suppression of lattice conduction path arising due to lattice distortion as confirmed from impedance analysis.     

The comparison between the effects of solvent casting and melt intercalation mixing processes on different characteristics of polylactide‐nanographite platelets composites

This study investigates the influence of enhanced dispersion of nanographite platelets (NGP) fillers through solvent casting mixing process on rheological, electrical and thermal properties of polylactide (PLA)/NGP composites. PLA/NGP composites were fabricated at 1 to 5 wt% filler contents by means of three processing techniques: (i) dry mixing and melt intercalation; (ii) solvent casting using dichloromethane organic solvent; and (iii) combination of solvent casting and melt intercalation techniques. The extent of dispersion of nanofillers within polymer matrix was evaluated through X‐ray diffraction and transmission electron microscopy analysis of the composites. Morphological studies of the samples revealed that the maximum extent of dispersion of NGP fillers within PLA matrix was achieved when the combination of solvent casting and melt intercalation processes occurred. Rheological analyses of the samples were indicative of deterioration in the composites produced through solvent casting mixing process. Despite of initial reduction in electrical resistivity of the composites after the addition of 1 wt% of NGP fillers, further addition of nanofillers did not exhibit a considerable enhancement in their electrical conductivity of the composites. Thermogravimetric analysis of the composites was demonstrative of enhancing impact of nanofiller loading, along with detrimental effect of solvent casting on the thermal stability of the PLA matrix. POLYM. ENG. SCI., 55:1560–1570, 2015. © 2014 Society of Plastics Engineers     

On the structural and electrical properties of modified PbTiO3 ceramics

Ceramics (Pb_0·75Ca_0·25)[(Ni_1/2W_1/2) _y Ti_1−y ]O₃ fory = 0 ·05, 0·10, 0·15 and 0·30 have been prepared using high temperature solid state reaction method. X-ray analyses show that these materials are of single-phase perovskite type tetragonal structure. To solve inaccuracy in finding para-ferroelectric phase transition temperatureT _c(ε _max), we have carried out the analyses of the data using a computer program. The role of Ni and W as modifiers on structural and electrical (dielectric and pyroelectric) properties is discussed in terms of the usefulness of these materials. Results indicate that ceramic Pb_0·75Ca_0·25Ni_0·25W_0·025Ti_0·95O₃ is a good candidate for pyroelectric applications. Paper presented at the poster session of MRSI AGM VI, Kharagpur, 1995