Log-modified Weibull regression models with censored data: Sensitivity and residual analysis

This paper proposes a regression model considering the modified Weibull distribution. This distribution can be used to model bathtub-shaped failure rate functions. Assuming censored data, we consider maximum likelihood and Jackknife estimators for the parameters of the model. We derive the appropriate matrices for assessing local influence on the parameter estimates under different perturbation schemes and we also present some ways to perform global influence. Besides, for different parameter settings, sample sizes and censoring percentages, various simulations are performed and the empirical distribution of the modified deviance residual is displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be straightforwardly extended for a martingale-type residual in log-modified Weibull regression models with censored data. Finally, we analyze a real data set under log-modified Weibull regression models. A diagnostic analysis and a model checking based on the modified deviance residual are performed to select appropriate models. (c) 2008 Elsevier B.V. All rights reserved.

Regression models for grouped survival data: Estimation and sensitivity analysis

In this study, regression models are evaluated for grouped survival data when the effect of censoring time is considered in the model and the regression structure is modeled through four link functions. The methodology for grouped survival data is based on life tables, and the times are grouped in k intervals so that ties are eliminated. Thus, the data modeling is performed by considering the discrete models of lifetime regression. The model parameters are estimated by using the maximum likelihood and jackknife methods. To detect influential observations in the proposed models, diagnostic measures based on case deletion, which are denominated global influence, and influence measures based on small perturbations in the data or in the model, referred to as local influence, are used. In addition to those measures, the local influence and the total influential estimate are also employed. Various simulation studies are performed and compared to the performance of the four link functions of the regression models for grouped survival data for different parameter settings, sample sizes and numbers of intervals. Finally, a data set is analyzed by using the proposed regression models. (C) 2010 Elsevier B.V. All rights reserved.

A Log-Linear Regression Model for the Beta-Weibull Distribution

We introduce the log-beta Weibull regression model based on the beta Weibull distribution (Famoye et al., 2005; Lee et al., 2007). We derive expansions for the moment generating function which do not depend on complicated functions. The new regression model represents a parametric family of models that includes as sub-models several widely known regression models that can be applied to censored survival data. We employ a frequentist analysis, a jackknife estimator, and a parametric bootstrap for the parameters of the proposed model. We derive the appropriate matrices for assessing local influences on the parameter estimates under different perturbation schemes and present some ways to assess global influences. Further, for different parameter settings, sample sizes, and censoring percentages, several simulations are performed. In addition, the empirical distribution of some modified residuals are displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be extended to a modified deviance residual in the proposed regression model applied to censored data. We define martingale and deviance residuals to evaluate the model assumptions. The extended regression model is very useful for the analysis of real data and could give more realistic fits than other special regression models.

Refractive index tomography of turbid media by bifocal optical coherence refractometry

We demonstrate tomographic imaging of the refractive index of turbid media using bifocal optical coherence refractometry (BOCR). The technique, which is a variant of optical coherence tomography, is based on the measurement of the optical pathlength difference between two foci simultaneously present in a medium of interest. We describe a new method to axially shift the bifocal optical pathlength that avoids the need to physically relocate the objective lens or the sample during an axial scan, and present an experimental realization based on an adaptive liquid-crystal lens. We present experimental results, including video clips, which demonstrate refractive index tomography of a range of turbid liquid phantoms, as well as of human skin in vivo.

The Genus Wolbachia

Numerous invertebrate species form long lasting symbioses with bacteria (Buchner, 1949; Buchner, 1965). One of the most common of these bacterial symbionts is Wolbachia pipientis, which has been estimated to infect anywhere from 15–75% of all insect species (Werren et al., 1995a; West et al., 1998; Jeyaprakash and Hoy, 2000; Werren and Windsor, 2000) as well as many species of arachnids, terrestrial crustaceans and filarial nematodes (O’Neill et al., 1997a; Bandi et al., 1998). In most arthropod associations, Wolbachia act as reproductive parasites manipulating the reproduction of their hosts to enhance their own vertical transmission. There appears to be little direct fitness cost to the infected host besides the costs arising from the reproductive manipulations. However instances have been reported where Wolbachia can be either deleterious (Min and Benzer, 1997; Bouchon et al., 1998) or beneficial (Girin and Boultreau, 1995; Stolk and Stouthamer, 1995; Wade and Chang, 1995; Vavre et al., 1999b; Dedeine et al., 2001) to their hosts. Wolbachia were first described as intracellular Rickettsia-like organisms (RLOs), infecting the gonad cells of the mosquito, Culex pipiens (Hertig and Wolbach, 1924), and were later named 'Wolbachia pipientis' (Hertig, 1936). It was not until the work of Yen and Barr (Yen and Barr, 1971; Yen and Barr, 1973) that Wolbachia were implicated in causing crossing incompatibilities between different mosquito populations (Laven, 1951; Ghelelovitch, 1952). When polymerase chain reaction (PCR) diagnostics for Wolbachia became available, it became clear that this agent was both extremely widespread and also responsible for a range of different reproductive phenotypes in the different hosts it infected (O’Neill et al., 1992; Rousset et al., 1992; Stouthamer et al., 1993). The most common of these are cytoplasmic incompatibility, inducing parthenogenesis, overriding host sex-determination, and male-killing (O’Neill et al., 1997a). As of the time of this writing, more than 450 different Wolbachia strains with unique gene sequences, different phenotypes, and infecting different hosts have been deposited in GenBank and the Wolbachia host database (http://www.wolbachia.sols. uq.edu.au).

Investigations into effective methods for assessing the condition of insulation in aged power transformers

This paper investigates the effective diagnostic technique(s) for assessing the condition of insulation in aged power transformers. A number of electrical, mechanical and chemical techniques were investigated. Many of these techniques are already used by the utility engineers and two comparatively new techniques are proposed in this paper. Results showing the effectiveness of these diagnostics are presented and correlation between the techniques are also presented. Finally, merits and suitability of different techniques are discussed in this paper.

Anemia screening in potential female blood donors: comparison of two different quantitative methods

Anemia screening before blood donation requires an accurate, quick, practical, and easy method with minimal discomfort for the donors. The aim of this study was to compare the accuracy of two quantitative methods of anemia screening: the HemoCue 201(+) (Aktiebolaget Leo Diagnostics) hemoglobin (Hb) and microhematocrit (micro-Hct) tests. Two blood samples of a single fingerstick were obtained from 969 unselected potential female donors to determine the Hb by HemoCue 201(+) and micro-Hct using HemataSTAT II (Separation Technology, Inc.), in alternating order. From each participant, a venous blood sample was drawn and run in an automatic hematology analyzer (ABX Pentra 60, ABX Diagnostics). Considering results of ABX Pentra 60 as true values, the sensitivity and specificity of HemoCue 201(+) and micro-Hct as screening methods were compared, using a venous Hb level of 12.0 g per dL as cutoff for anemia. The sensitivities of the HemoCue 201(+) and HemataSTAT II in detecting anemia were 56 percent (95% confidence interval [CI], 46.1%-65.5%) and 39.5 percent (95% CI, 30.2%-49.3%), respectively (p < 0.001). Analyzing only candidates with a venous Hb level lower than 11.0 g per dL, the deferral rate was 100 percent by HemoCue 201(+) and 77 percent by HemataSTAT II. The specificities of the methods were 93.5 and 93.2 percent, respectively. The HemoCue 201(+) showed greater discriminating power for detecting anemia in prospective blood donors than the micro-Hct method. Both presented equivalent deferral error rates of nonanemic potential donors. Compared to the micro-Hct, HemoCue 201(+) reduces the risk of anemic female donors giving blood, specially for those with lower Hb levels, without increasing the deferral of nonanemic potential donors.

Prevalence of diabetic peripheral neuropathy and relation to glycemic control therapies at baseline in the BARI 2D cohort

We evaluated the associations between glycemic therapies and prevalence of diabetic peripheral neuropathy (DPN) at baseline among participants in the Bypass Angioplasty Revascularization Investigation 2 Diabetes (BARI 2D) trial on medical and revascularization therapies for coronary artery disease (CAD) and on insulin-sensitizing vs. insulin-providing treatments for diabetes. A total of 2,368 patients with type 2 diabetes and CAD was evaluated. DPN was defined as clinical examination score > 2 using the Michigan Neuropathy Screening Instrument (MNSI). DPN odds ratios across different groups of glycemic therapy were evaluated by multiple logistic regression adjusted for multiple covariates including age, sex, hemoglobin A1c (HbA1c), and diabetes duration. Fifty-one percent of BARI 2D subjects with valid baseline characteristics and MNSI scores had DPN. After adjusting for all variables, use of insulin was significantly associated with DPN (OR = 1.57, 95% CI: 1.15-2.13). Patients on sulfonylurea (SU) or combination of SU/metformin (Met)/thiazolidinediones (TZD) had marginally higher rates of DPN than the Met/TZD group. This cross-sectional study in a cohort of patients with type 2 diabetes and CAD showed association of insulin use with higher DPN prevalence, independent of disease duration, glycemic control, and other characteristics. The causality between a glycemic control strategy and DPN cannot be evaluated in this cross-sectional study, but continued assessment of DPN and randomized therapies in BARI 2D trial may provide further explanations on the development of DPN.

High-breakdown linear discriminant analysis

The classification rules of linear discriminant analysis are defined by the true mean vectors and the common covariance matrix of the populations from which the data come. Because these true parameters are generally unknown, they are commonly estimated by the sample mean vector and covariance matrix of the data in a training sample randomly drawn from each population. However, these sample statistics are notoriously susceptible to contamination by outliers, a problem compounded by the fact that the outliers may be invisible to conventional diagnostics. High-breakdown estimation is a procedure designed to remove this cause for concern by producing estimates that are immune to serious distortion by a minority of outliers, regardless of their severity. In this article we motivate and develop a high-breakdown criterion for linear discriminant analysis and give an algorithm for its implementation. The procedure is intended to supplement rather than replace the usual sample-moment methodology of discriminant analysis either by providing indications that the dataset is not seriously affected by outliers (supporting the usual analysis) or by identifying apparently aberrant points and giving resistant estimators that are not affected by them.

Patterns of viral load in chronic hepatitis B patients in Brazil and their association with ALT levels and HBeAg status

Serum hepatitis B virus (HBV) DNA [eve[ is a predictor of the development of cirrhosis and hepatocellullar carcinoma in chronic hepatitis B patients. Nevertheless, the distribution of viral load levels in chronic HBV patients in Brazil has yet to be described. This cross-sectional study included 564 participants selected in nine Brazilian cities located in four of the five regions of the country using the database of a medical diagnostics company. Admission criteria included hepatitis B surface antigen seropositivity, availability of HBV viral toad samples and age >= 18 years. Mates comprised 64.5% of the study population. Mean age was 43.7 years. Most individuals (62.1%) were seronegative for the hepatitis B e antigen (HBeAg). Median serum ALT level was 34 U/L. In 58.5% of the patients HBV-DNA levels ranged from 300 to 99,999 copies/mL; however, in 21.6% levels were undetectable. Median HBV-DNA level was 2,351 copies/mL. Over 60% of the patients who tested negative for HBeAg and in whom ALT level was less than 1.5 times the upper limit of the normal range had HBV-DNA levels > 2,000 IU/mL, which has been considered a cut-off point for indicating a liver biopsy and/or treatment. In conclusion, HBV-DNA level identified a significant proportion of Brazilian individuals with chronic hepatitis B at risk of disease progression. Furthermore, this tool. enables those individuals with high HBV-DNA levels who are susceptible to disease progression to be identified among patients with normal or stightly elevated ALT.

Factors Related to the Selection of Surgical Versus Percutaneous Revascularization in Diabetic Patients With Multivessel Coronary Artery Disease in the BARI 2D (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes) Trial

Objectives We evaluated demographic, clinical, and angiographic factors influencing the selection of coronary artery bypass graft (CABG) surgery versus percutaneous coronary intervention (PCI) in diabetic patients with multivessel coronary artery disease (CAD) in the BARI 2D (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes) trial. Background Factors guiding selection of mode of revascularization for patients with diabetes mellitus and multivessel CAD are not clearly defined. Methods In the BARI 2D trial, the selected revascularization strategy, CABG or PCI, was based on physician discretion, declared independent of randomization to either immediate or deferred revascularization if clinically warranted. We analyzed factors favoring selection of CABG versus PCI in 1,593 diabetic patients with multivessel CAD enrolled between 2001 and 2005. Results Selection of CABG over PCI was declared in 44% of patients and was driven by angiographic factors including triple vessel disease (odds ratio [OR]: 4.43), left anterior descending stenosis >= 70% (OR: 2.86), proximal left anterior descending stenosis >= 50% (OR: 1.78), total occlusion (OR: 2.35), and multiple class C lesions (OR: 2.06) (all p < 0.005). Nonangiographic predictors of CABG included age >= 65 years (OR: 1.43, p = 0.011) and non-U.S. region (OR: 2.89, p = 0.017). Absence of prior PCI (OR: 0.45, p < 0.001) and the availability of drug-eluting stents conferred a lower probability of choosing CABG (OR: 0.60, p = 0.003). Conclusions The majority of diabetic patients with multivessel disease were selected for PCI rather than CABG. Preference for CABG over PCI was largely based on angiographic features related to the extent, location, and nature of CAD, as well as geographic, demographic, and clinical factors. (Bypass Angioplasty Revascularization Investigation in Type 2 Diabetes [BARI 2D]; NCT00006305) (J Am Coll Cardiol Intv 2009;2:384-92) (C) 2009 by the American College of Cardiology Foundation

Prospective survey of tick paralysis in dogs

Objective To obtain information on tick paralysis in dogs, including the nature of disease, host signalment, tick-host relationship, treatment, disease progression and recovery, and preventive measures. Design A prospective survey of 577 dogs affected by tick paralysis was conducted during 1998. Forty-two veterinary clinics along the eastern coast of Australia were instructed to complete survey forms for the first 15 dogs that presented with tick paralysis during September to November. Results Five percent of dogs died from tick paralysis. Younger dogs were more likely to survive. Long coat length was associated with a greater tick burden but not greater tick size, whereas coat thickness had no bearing on either. Dogs with mild disease recovered more quickly from tick paralysis. Respiratory and gait scores reflected disease severity and were good prognostic indicators. The size of the tick did not reflect the severity of the clinical condition it induced in the host. No method of tick removal or in situ treatment improved recovery time or reduced mortality. However, the time spent in hospital was significantly less for dogs from which the live tick was manually removed. Inspiratory strider. evident in some dogs with tick paralysis, was not related to tick attachment on the neck. The use of acepromazine maleate or dexamethasone did not reduce recovery time or mortality. Increasing the dose of tick antitoxin serum (TAS) above 0.1 mL/kg had no effect on mortality or recovery time. Dogs with severe disease that received an additional dose of TAS were significantly less likely to survive. Subcutaneous use of TAS at the site of tick attachment was of no benefit in reducing mortality or time to initial clinical improvement. A registered preventative product had not been used on the majority of dogs. Clipping the coat to search for ticks did not reduce mortality. Conclusions Therapy needs to address cardiopulmonary dysfunction that may be due directly to the effect of tick toxin and not just respiratory compromise caused by progressive respiratory muscle failure.

Valuing of firm's prior knowledge: A measure of knowledge distance

Knowledge, especially scientific and technological knowledge, grows according to knowledge trajectories and guideposts that make up the prior knowledge of an organization. We argue that these knowledge structures and their specific components lead to successful innovation. A firm's prior knowledge facilitates the absorption of new knowledge, thereby renewing a firm's systematic search, transfer and acquisition of knowledge and capabilities. In particular, the exponential growth in biotechnology is characterized by the convergence of disparate scientific and technological knowledge resources. This paper examines the shift from protein-based to DNA-based diagnostic technologies as an example, to quantify the value of a firm's prior knowledge using relative values of knowledge distance. The distance between core prior knowledge and the rate of transition from one knowledge system to another has been identified as a proxy for the value a firm's prior knowledge. The overall difficulty of transition from one technology paradigm to another is discussed. We argue this transition is possible when the knowledge distance is minimal and the transition process has a correspondingly high value of absorptive capacities. Our findings show knowledge distance is a determinant of the feasibility, continuity and capture of scientific and technological knowledge. Copyright © 2003 John Wiley & Sons, Ltd.

Review of time-domain polarization measurements for assessing insulation condition in aged transformers

This paper presents a review of the time-domain polarization measurement techniques for the condition assessment of aged transformer insulation. The polarization process is first described with appropriate dielectric response theories and then commonly used polarization methods are described with special emphasis on the most widely used return voltage(rv) measurement. Most recent emphasis has been directed to techniques of determining moisture content of insulation indirectly by measuring rv parameters. The major difficulty still lies with the accurate interpretation of return voltage results. This paper investigates different thoughts regarding the interpretation of rv results for different moisture and ageing conditions. Other time domain polarization measurement techniques and their results are also presented in this paper.