Model Checking for ROC Regression Analysis

The Receiver Operating Characteristic (ROC) curve is a prominent tool for characterizing the accuracy of continuous diagnostic test. To account for factors that might invluence the test accuracy, various ROC regression methods have been proposed. However, as in any regression analysis, when the assumed models do not fit the data well, these methods may render invalid and misleading results. To date practical model checking techniques suitable for validating existing ROC regression models are not yet available. In this paper, we develop cumulative residual based procedures to graphically and numerically assess the goodness-of-fit for some commonly used ROC regression models, and show how specific components of these models can be examined within this framework. We derive asymptotic null distributions for the residual process and discuss resampling procedures to approximate these distributions in practice. We illustrate our methods with a dataset from the Cystic Fibrosis registry.

On the Accelerated Failure Time Model for Current Status and Interval Censored Data

This paper introduces a novel approach to making inference about the regression parameters in the accelerated failure time (AFT) model for current status and interval censored data. The estimator is constructed by inverting a Wald type test for testing a null proportional hazards model. A numerically efficient Markov chain Monte Carlo (MCMC) based resampling method is proposed to simultaneously obtain the point estimator and a consistent estimator of its variance-covariance matrix. We illustrate our approach with interval censored data sets from two clinical studies. Extensive numerical studies are conducted to evaluate the finite sample performance of the new estimators.

A unified approach to modeling multivariate binary data using copulas over partitions

Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate that many current approaches for marginal modeling of correlated binary outcomes produce likelihoods that are equivalent to the proposed copula-based models herein. These general copula models of underlying latent threshold random variables yield likelihood based models for marginal fixed effects estimation and interpretation in the analysis of correlated binary data. Moreover, we propose a nomenclature and set of model relationships that substantially elucidates the complex area of marginalized models for binary data. A diverse collection of didactic mathematical and numerical examples are given to illustrate concepts.

Natural killer T cell dysfunction in CD39-null mice protects against concanavalin A-induced hepatitis

Concanavalin A (Con A)-induced injury is an established natural killer T (NKT) cell-mediated model of inflammation that has been used in studies of immune liver disease. Extracellular nucleotides, such as adenosine triphosphate, are released by Con A-stimulated cells and bind to specific purinergic type 2 receptors to modulate immune activation responses. Levels of extracellular nucleotides are in turn closely regulated by ectonucleotidases, such as CD39/NTPDase1. Effects of extracellular nucleotides and CD39 on NKT cell activation and upon hepatic inflammation have been largely unexplored to date. Here, we show that NKT cells express both CD39 and CD73/ecto-5'-nucleotidase and can therefore generate adenosine from extracellular nucleotides, whereas natural killer cells do not express CD73. In vivo, mice null for CD39 are protected from Con A-induced liver injury and show substantively lower serum levels of interleukin-4 and interferon-gamma when compared with matched wild-type mice. Numbers of hepatic NKT cells are significantly decreased in CD39 null mice after Con A administration. Hepatic NKT cells express most P2X and P2Y receptors; exceptions include P2X3 and P2Y11. Heightened levels of apoptosis of CD39 null NKT cells in vivo and in vitro appear to be driven by unimpeded activation of the P2X7 receptor. CONCLUSION: CD39 and CD73 are novel phenotypic markers of NKT cells. Deletion of CD39 modulates nucleotide-mediated cytokine production by, and limits apoptosis of, hepatic NKT cells providing protection against Con A-induced hepatitis. This study illustrates a further role for purinergic signaling in NKT-mediated mechanisms that result in liver immune injury.

Multivariate modelling of responses to conditional items: New possibilities for latent class analysis

Questionnaire data may contain missing values because certain questions do not apply to all respondents. For instance, questions addressing particular attributes of a symptom, such as frequency, triggers or seasonality, are only applicable to those who have experienced the symptom, while for those who have not, responses to these items will be missing. This missing information does not fall into the category 'missing by design', rather the features of interest do not exist and cannot be measured regardless of survey design. Analysis of responses to such conditional items is therefore typically restricted to the subpopulation in which they apply. This article is concerned with joint multivariate modelling of responses to both unconditional and conditional items without restricting the analysis to this subpopulation. Such an approach is of interest when the distributions of both types of responses are thought to be determined by common parameters affecting the whole population. By integrating the conditional item structure into the model, inference can be based both on unconditional data from the entire population and on conditional data from subjects for whom they exist. This approach opens new possibilities for multivariate analysis of such data. We apply this approach to latent class modelling and provide an example using data on respiratory symptoms (wheeze and cough) in children. Conditional data structures such as that considered here are common in medical research settings and, although our focus is on latent class models, the approach can be applied to other multivariate models.

Serum metabolomics reveals irreversible inhibition of fatty acid beta-oxidation through the suppression of PPARalpha activation as a contributing mechanism of acetaminophen-induced hepatotoxicity

Metabolic bioactivation, glutathione depletion, and covalent binding are the early hallmark events after acetaminophen (APAP) overdose. However, the subsequent metabolic consequences contributing to APAP-induced hepatic necrosis and apoptosis have not been fully elucidated. In this study, serum metabolomes of control and APAP-treated wild-type and Cyp2e1-null mice were examined by liquid chromatography-mass spectrometry (LC-MS) and multivariate data analysis. A dose-response study showed that the accumulation of long-chain acylcarnitines in serum contributes to the separation of wild-type mice undergoing APAP-induced hepatotoxicity from other mouse groups in a multivariate model. This observation, in conjunction with the increase of triglycerides and free fatty acids in the serum of APAP-treated wild-type mice, suggested that APAP treatment can disrupt fatty acid beta-oxidation. A time-course study further indicated that both wild-type and Cyp2e1-null mice had their serum acylcarnitine levels markedly elevated within the early hours of APAP treatment. While remaining high in wild-type mice, serum acylcarnitine levels gradually returned to normal in Cyp2e1-null mice at the end of the 24 h treatment. Distinct from serum aminotransferase activity and hepatic glutathione levels, the pattern of serum acylcarnitine accumulation suggested that acylcarnitines can function as complementary biomarkers for monitoring the APAP-induced hepatotoxicity. An essential role for peroxisome proliferator-activated receptor alpha (PPARalpha) in the regulation of serum acylcarnitine levels was established by comparing the metabolomic responses of wild-type and Ppara-null mice to a fasting challenge. The upregulation of PPARalpha activity following APAP treatment was transient in wild-type mice but was much more prolonged in Cyp2e1-null mice. Overall, serum metabolomics of APAP-induced hepatotoxicity revealed that the CYP2E1-mediated metabolic activation and oxidative stress following APAP treatment can cause irreversible inhibition of fatty acid oxidation, potentially through suppression of PPARalpha-regulated pathways.

Metabolomics reveals a novel vitamin E metabolite and attenuated vitamin E metabolism upon PXR activation

Pregnane X receptor (PXR) is an important nuclear receptor xenosensor that regulates the expression of metabolic enzymes and transporters involved in the metabolism of xenobiotics and endobiotics. In this study, ultra-performance liquid chromatography (UPLC) coupled with electrospray time-of-flight mass spectrometry (TOFMS), revealed altered urinary metabolomes in both Pxr-null and wild-type mice treated with the mouse PXR activator pregnenolone 16alpha-carbonitrile (PCN). Multivariate data analysis revealed that PCN significantly attenuated the urinary vitamin E metabolite alpha-carboxyethyl hydroxychroman (CEHC) glucuronide together with a novel metabolite in wild-type but not Pxr-null mice. Deconjugation experiments with beta-glucuronidase and beta-glucosidase suggested that the novel urinary metabolite was gamma-CEHC beta-D-glucoside (Glc). The identity of gamma-CEHC Glc was confirmed by chemical synthesis and by comparing tandem mass fragmentation of the urinary metabolite with the authentic standard. The lower urinary CEHC was likely due to PXR-mediated repression of hepatic sterol carrier protein 2 involved in peroxisomal beta-oxidation of branched-chain fatty acids (BCFA). Using a combination of metabolomic analysis and a genetically modified mouse model, this study revealed that activation of PXR results in attenuated levels of the two vitamin E conjugates, and identification of a novel vitamin E metabolite, gamma-CEHC Glc. Activation of PXR results in attenuated levels of the two vitamin E conjugates that may be useful as biomarkers of PXR activation.

Datenanalyse. Das Null-Ritual und der Umgang mit Effekten in der Zeitschrift für Sportpsychologie

Ziel dieses Beitrages ist die Analyse der Anwendung empirischer Tests in der deutschsprachigen Sportpsychologie. Die Ergebnisse vergleichbarer Analysen, bspw. in der Psychologie, zeigen, dass zwischen Anforderungen aus Testkonzepten und empirischer Realität Unterschiede existieren, die bislang für die Sportpsychologie nicht beschrieben und bewertet worden sind. Die Jahrgänge 1994–2007 der Zeitschrift für Sportpsychologie (früher psychologie und sport) wurden danach untersucht, ob Forschungsfragen formuliert, welche Stichprobenart gewählt, welches Testkonzept verwendet, welches Signifikanzniveau benutzt und ob statistische Probleme diskutiert wurden. 83 Artikel wurden von zwei unabhängigen Bewertern nach diesen Aspekten kategorisiert. Als Ergebnis ist festzuhalten, dass in der sportpsychologischen Forschung überwiegend eine Mischung aus Fishers Signifikanztesten sowie Neyman-Pearsons-Hypothesentesten zur Anwendung kommt,das sogenannte „Hybrid-Modell” oder „Null-Ritual”. Die Beschreibung der Teststärke ist kaum zu beobachten. Eine zeitliche Analyse der Beiträge zeigt, dass vor allem die Benutzung von Effektgrößen in den letzten Jahren zugenommen hat. Abschließend werden Ansätze zur Verbesserung und der Vereinheitlichung der Anwendung empirischer Tests vorgeschlagen und diskutiert.

Meta-model for calculating the mean energy demand of automated storage and retrieval systems

Energy efficiency has become an important research topic in intralogistics. Especially in this field the focus is placed on automated storage and retrieval systems (AS/RS) utilizing stacker cranes as these systems are widespread and consume a significant portion of the total energy demand of intralogistical systems. Numerical simulation models were developed to calculate the energy demand rather precisely for discrete single and dual command cycles. Unfortunately these simulation models are not suitable to perform fast calculations to determine a mean energy demand value of a complete storage aisle. For this purpose analytical approaches would be more convenient but until now analytical approaches only deliver results for certain configurations. In particular, for commonly used stacker cranes equipped with an intermediate circuit connection within their drive configuration there is no analytical approach available to calculate the mean energy demand. This article should address this research gap and present a calculation approach which enables planners to quickly calculate the energy demand of these systems.

ANOVA kernels and RKHS of zero mean functions for model-based sensitivity analysis

Given a reproducing kernel Hilbert space (H,〈.,.〉)(H,〈.,.〉) of real-valued functions and a suitable measure μμ over the source space D⊂RD⊂R, we decompose HH as the sum of a subspace of centered functions for μμ and its orthogonal in HH. This decomposition leads to a special case of ANOVA kernels, for which the functional ANOVA representation of the best predictor can be elegantly derived, either in an interpolation or regularization framework. The proposed kernels appear to be particularly convenient for analyzing the effect of each (group of) variable(s) and computing sensitivity indices without recursivity.

Evaluation and Model of a Clinical Librarian Program

Clinical medical librarianship is entering its second decade, but little evaluative data has accrued in the literature. Variations from the original programs and novel new approaches have insured the survival of the program so far. The clinical librarian (CL) forms a vital link between the library and the health care professional, operating as an important information transfer agent. However, to further insure the survival of these vital programs, hard evaluative evidence is needed. The University of Texas Medical Branch (UTMB) at Galveston began a CL Program in 1978/79. An extensive three-year pre/post evaluation study was conducted using a specifically developed evaluation model, which, if adopted by others, will provide the needed comparative data. Both a pilot study, or formative evaluation, and a summative evaluation were conducted. The results of this evaluation confirmed many of the conclusions reported by other CL programs. Eight hypotheses were proposed at the beginning of this study. Data were collected and used to support acceptance or rejection of the null hypotheses, and conclusions were drawn according to the results. Implications relevant to the study conclusions and future trends in medical librarianship are also discussed in the closing chapter.

Simulation of Drosophila circadian oscillations, mutations, and light responses by a model with VRI, PDP-1, and CLK.

A model of Drosophila circadian rhythm generation was developed to represent feedback loops based on transcriptional regulation of per, Clk (dclock), Pdp-1, and vri (vrille). The model postulates that histone acetylation kinetics make transcriptional activation a nonlinear function of [CLK]. Such a nonlinearity is essential to simulate robust circadian oscillations of transcription in our model and in previous models. Simulations suggest that two positive feedback loops involving Clk are not essential for oscillations, because oscillations of [PER] were preserved when Clk, vri, or Pdp-1 expression was fixed. However, eliminating positive feedback by fixing vri expression altered the oscillation period. Eliminating the negative feedback loop in which PER represses per expression abolished oscillations. Simulations of per or Clk null mutations, of per overexpression, and of vri, Clk, or Pdp-1 heterozygous null mutations altered model behavior in ways similar to experimental data. The model simulated a photic phase-response curve resembling experimental curves, and oscillations entrained to simulated light-dark cycles. Temperature compensation of oscillation period could be simulated if temperature elevation slowed PER nuclear entry or PER phosphorylation. The model makes experimental predictions, some of which could be tested in transgenic Drosophila.