Physical Sciences and Mathematics Commons^™

Applications Of Some Improved Estimators In Linear Regression, B. M. Golam Kibria

Journal of Modern Applied Statistical Methods

The problem of estimation of the regression coefficients under multicollinearity situation for the restricted linear model is discussed. Some improve estimators are considered, including the unrestricted ridge regression estimator (URRE), restricted ridge regression estimator (RRRE), shrinkage restricted ridge regression estimator (SRRRE), preliminary test ridge regression estimator (PTRRE), and restricted Liu estimator (RLIUE). The were compared based on the sampling variance-covariance criterion. The RRRE dominates other ridge estimators when the restriction does or does not hold. A numerical example was provided. The RRRE performed equivalently or better than the RLIUE in the sense of having smaller sampling variance.

Incorporating Death Into Health-Related Variables In Longitudinal Studies, Paula Diehr, Laura Lee Johnson, Donald L. Patrick, Bruce Psaty

UW Biostatistics Working Paper Series

Background: The aging process can be described as the change in health-related variables over time. Unfortunately, simple graphs of available data may be misleading if some people die, since they may confuse patterns of mortality with patterns of change in health. Methods have been proposed to incorporate death into self-rated health (excellent to poor) and the SF-36 profile scores, but not for other variables.

Objectives: (1) To incorporate death into the following variables: ADLs, IADLs, mini-mental state examination, depressive symptoms, body mass index (BMI), blocks walked per week, bed days, hospitalization, systolic blood pressure, and the timed walk. (2) To …

Extrinsic Control Of The Exchange Bias, Christian Binek

Christian Binek Publications

A new control mechanism for the exchange bias effect in magnetic heterostructures is proposed. It takes advantage of the magnetoelectric effect which takes place in the antiferromagnetic pinning layer. In contrast with the pioneering AC measurements of the magnetoelectric effect, we investigate the magnetic response of the prototypical magnetoelectric compound Cr2O3 on static electric fields. The linear dependence of the magnetic moment on the applied axial electric field and the temperature dependence of the corresponding slopes αshort parallel are measured by DC SQUID magnetometry. The contribution of the field-induced surface magnetization and its impact on the exchange bias effect is …

Not All Effects Are Created Equal: A Rejoinder To Sawilowsky, J. Kyle Roberts, Robin K. Henson

Journal of Modern Applied Statistical Methods

In the continuing debate over the use and utility of effect sizes, more discussion often helps to both clarify and syncretize methodological views. Here, further defense is given of Roberts & Henson (2002) in terms of measuring bias in Cohen’s d, and a rejoinder to Sawilowsky (2003) is presented.

Comparing Correlated Parameter Estimates For Nonlinear Pet Model, J. Wu, A. Parkhurst, K. Eskridge, D. Travnicek, T. Brown-Brandi, R. Eigenberg, G. L. Hahn, J. Nienaber, T. Mader, D. Spiers

Conference on Applied Statistics in Agriculture

The nonlinear PET model based on Newton's law of cooling can be used to estimate body temperature in cattle, T _b challenged by hot cyclic chamber temperatures, T _a . The PET model has four biologically meaningful parameters: K, the thermal constant; Δ, the difference between T _b and adjusted T _a ; Υ the proportion of variation in T _b comparable to variation in T_a ; T _bini, the initial body temperature. The two parameters Y and Δ are highly correlated in the current version of the model. This study looks at other ways to parameterize …

Exploration Of Distributions Of Ratio Of Partial Sum Of Sample Eigenvalues When All Population Eigenvalues Are The Same, Moonseong Heo

Journal of Modern Applied Statistical Methods

This paper explores empirically the first two moments of ratio of the partial sum of the first two sample eigenvalues to the sum of all eigenvalues when the population eigenvalues of a covariance matrix are all the same. Estimation of the first two moments can be practically crucial in assessing non-randomness of observed patterns on planar graphical displays based on lower rank approximations of data matrices. For derivation of the moments, exact and large sample asymptotic distributions of the sample ratios are reviewed but neither can be applicable to derivation of the moments. Therefore, I rely on simulations, where data …

Exchange Bias In Fef20-Copt Heterosystems With Perpendicular Anisotropy, Christian Binek

Christian Binek Publications

The previous exchange bias effect is measured in heterosystems with perpendicular anisotropy consisting of Co/Pt multilayers on top of the (0 0 1) face of a previous FeF2 single crystal. The resulting previous exchange field HE exhibits a strong dependence on temperature and the axial freezing field, HF. Within the framework of an Ising-type model, the HE vs. T as well as the HE vs. HF data are explained in terms of the microscopic spin structure at the interface.

Exchange Bias In Fe0.6zn0.4f2 Heterostructures, Christian Binek

Christian Binek Publications

The previous exchange bias field, He, is measured in Fe0.6Zn0.4F2/Fe heterosystems prepared from Fe layers of 14 and 5 nm thickness which are deposited on top of the compensated (1 1 0) surface of the antiferromagnet. Deviations from a linear dependence of He on the magnetization of the Fe layer are attributed to ferromagnetic domains. Moreover, piezomagnetism and its influence on He are evidenced.

Exchange Bias In A Generalized Meiklejohn-Bean Approach, Christian Binek

Christian Binek Publications

A generalized Meiklejohn–Bean model is considered in order to derive an analytic expression for the dependence of the previous exchange bias term field on the layer thickness involved in ferromagnetic/antiferromagnetic heterosystems, on the orientation of the applied magnetic field with respect to the magnetic easy axes and on the quenched magnetization MAF of the antiferromagnetic pinning layer. While MAF is a well-known feature of field-cooled dilute antiferromagnets, it seems to occur quite generally also in pure AF pinning substrates. The new analytic expressions are successfully compared with recent experimental results and Monte Carlo investigations.

Bias And The Probability Of Generalization, Tony R. Martinez, D. Randall Wilson

Faculty Publications

In order to be useful, a learning algorithm must be able to generalize well when faced with inputs not previously presented to the system. A bias is necessary for any generalization, and as shown by several researchers in recent years, no bias can lead to strictly better generalization than any other when summed over all possible functions or applications. This paper provides examples to illustrate this fact, but also explains how a bias or learning algorithm can be “better” than another in practice when the probability of the occurrence of functions is taken into account. It shows how domain knowledge …

Sources Of Epidemiological Equivocacy, Timothy Sly

RISK: Health, Safety & Environment (1990-2002)

Mr. Sly discusses five sources of uncertainty and ambiguity in health and medical research that can interfere with decision making.

Environmental Racism And Biased Methods Of Risk Assessment, Daniel C. Wigley, Kristin S. Shrader-Frechette

RISK: Health, Safety & Environment (1990-2002)

Based on analysis of a risk assessment for a proposed Louisiana uranium enrichment facility, the authors argue that environmental injustice occurs when assessors' scientific methods cause de facto discrimination.

Review Of: It Just Ain't Fair: The Ethics Of Health Care For African Americans (Annette Dula & Sara Goering Eds.), Carrie Anne Juliano

RISK: Health, Safety & Environment (1990-2002)

Review of: It Just Ain't Fair: The Ethics of Health Care for African Americans (Annette Dula & Sara Goering eds., Praeger 1994) About the editors and contributors, acknowledgements, bibliography, foreword by Mark Siegler, index, notes. L.C. 93-43780, ISBN 0-275-94494-8. [ 336 pp. Paper $19.95. P.O. Box 5007, Westport CT 06881-5007.]

Treatment Modality And Quality Differences For Black And White Breast Cancer Patients Treated In Community Hospitals, Paula Diehr

Paula Diehr

This study assessed the relationship of race and patterns of care, defined by an expert NCI-appointed committee, for 7,781 patients with breast cancer treated in 107 hospitals in 45 communities between 1982 and 1985. After control for age and stage of disease, black patients had significantly different care from white patients for four of the ten patterns examined. They were less likely to have a progesterone receptor assay or to be referred for postmastectomy rehabilitation, two patterns deemed desirable for all patients. Black patients were also more likely to receive liver scans and radiation therapy in situations in which these …

The Effect Of Age On The Care Of Women With Breast Cancer In Community Hospitals, Paula Diehr, Joe Chu

Paula Diehr

We studied the process of care received by 1,680 female breast cancer patients treated in 17 community hospitals. The probability of receiving various diagnostic, consultation, therapy, or rehabilitation services was almost always significantly associated with patient age for one or more disease stages. Most often there was a linear trend for older patients to receive fewer services (e.g., biopsies prior to definitive treatment, number of lymph nodes examined, chemotherapy, radiation therapy) but other age patterns also were found. Age was not significantly associated with clinical staging or estrogen receptors.

Correction Of Bias In Estimating Autocovariance Function, Len-Hong Wu

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

The purpose of this thesis was to evaluate a method for reducing the bias of estimation for autocovariance estimators. Two methods are compared, one is the standard method and the other is an adjustment method. The Monte Carlo method is used within comparison.

The bias and the mean squared error of the estimated autocovariance is computed for several time series models and two variations of the adjustment method of estimation. The results indicate some improvement in bias and mean squared error for the new method.