Aging Intensity for Step-Stress Accelerated Life Testing Experiments.

The aging intensity (AI), defined as the ratio of the instantaneous hazard rate and a baseline hazard rate, is a useful tool for the describing reliability properties of a random variable corresponding to a lifetime. In this work, the concept of AI is introduced in step-stress accelerated life testing (SSALT) experiments, providing new insights to the model and enabling the further clarification of the differences between the two commonly employed cumulative exposure (CE) and tampered failure rate (TFR) models. New AI-based estimators for the parameters of a SSALT model are proposed and compared to the MLEs in terms of examples and a simulation study.

Exact Mediation Analysis for Ordinal Outcome and Binary Mediator.

With reference to a single mediator context, this brief report presents a model-based strategy to estimate counterfactual direct and indirect effects when the response variable is ordinal and the mediator is binary. Postulating a logistic regression model for the mediator and a cumulative logit model for the outcome, we present the exact parametric formulation of the causal effects, thereby extending previous work that only contained approximated results. The identification conditions are equivalent to the ones already established in the literature. The effects can be estimated by making use of standard statistical software and standard errors can be computed via a bootstrap algorithm. To make the methodology accessible, routines to implement the proposal in R are presented in the eAppendix; http://links.lww.com/EDE/B962. We also derive the natural effect model coherent with the postulated data-generating mechanism.

Asymptotic Posterior Normality of Multivariate Latent Traits in an IRT Model.

The asymptotic posterior normality (APN) of the latent variable vector in an item response theory (IRT) model is a crucial argument in IRT modeling approaches. In case of a single latent trait and under general assumptions, Chang and Stout (Psychometrika, 58(1):37-52, 1993) proved the APN for a broad class of latent trait models for binary items. Under the same setup, they also showed the consistency of the latent trait's maximum likelihood estimator (MLE). Since then, several modeling approaches have been developed that consider multivariate latent traits and assume their APN, a conjecture which has not been proved so far. We fill this theoretical gap by extending the results of Chang and Stout for multivariate latent traits. Further, we discuss the existence and consistency of MLEs, maximum a-posteriori and expected a-posteriori estimators for the latent traits under the same broad class of latent trait models.

ϕ-Divergence in Contingency Table Analysis.

The ϕ -divergence association models for two-way contingency tables is a family of models that includes the association and correlation models as special cases. We present this family of models, discussing its features and demonstrating the role of ϕ -divergence in building this family. The most parsimonious member of this family, the model of ϕ -scaled uniform local association, is considered in detail. It is implemented and representative examples are commented on.

Ordinal probability effect measures for group comparisons in multinomial cumulative link models.

We consider simple ordinal model-based probability effect measures for comparing distributions of two groups, adjusted for explanatory variables. An "ordinal superiority" measure summarizes the probability that an observation from one distribution falls above an independent observation from the other distribution, adjusted for explanatory variables in a model. The measure applies directly to normal linear models and to a normal latent variable model for ordinal response variables. It equals Φ(ß/2) for the corresponding ordinal model that applies a probit link function to cumulative multinomial probabilities, for standard normal cdf Φ and effect ß that is the coefficient of the group indicator variable. For the more general latent variable model for ordinal responses that corresponds to a linear model with other possible error distributions and corresponding link functions for cumulative multinomial probabilities, the ordinal superiority measure equals exp(ß)/[1+exp(ß)] with the log-log link and equals approximately exp(ß/2)/[1+exp(ß/2)] with the logit link, where ß is the group effect. Another ordinal superiority measure generalizes the difference of proportions from binary to ordinal responses. We also present related measures directly for ordinal models for the observed response that need not assume corresponding latent response models. We present confidence intervals for the measures and illustrate with an example.

Murine pheromone proteins constitute a context-dependent combinatorial code governing multiple social behaviors.

During social interactions, an individual's behavior is largely governed by the subset of signals emitted by others. Discrimination of "self" from "other" regulates the territorial urine countermarking behavior of mice. To identify the cues for this social discrimination and understand how they are interpreted, we designed an olfactory-dependent countermarking assay. We find major urinary proteins (MUPs) sufficient to elicit countermarking, and unlike other vomeronasal ligands that are detected by specifically tuned sensory neurons, MUPs are detected by a combinatorial strategy. A chemosensory signature of "self" that modulates behavior is developed via experience through exposure to a repertoire of MUPs. In contrast, aggression can be elicited by MUPs in an experience-independent but context-dependent manner. These findings reveal that individually emitted chemical cues can be interpreted based on their combinatorial permutation and relative ratios, and they can transmit both fixed and learned information to promote multiple behaviors.

GEE for multinomial responses using a local odds ratios parameterization.

In this article, we propose a generalized estimating equations (GEE) approach for correlated ordinal or nominal multinomial responses using a local odds ratios parameterization. Our motivation lies upon observing that: (i) modeling the dependence between correlated multinomial responses via the local odds ratios is meaningful both for ordinal and nominal response scales and (ii) ordinary GEE methods might not ensure the joint existence of the estimates of the marginal regression parameters and of the dependence structure. To avoid (ii), we treat the so-called "working" association vector α as a "nuisance" parameter vector that defines the local odds ratios structure at the marginalized contingency tables after tabulating the responses without a covariate adjustment at each time pair. To estimate α and simultaneously approximate adequately possible underlying dependence structures, we employ the family of association models proposed by Goodman. In simulations, the parameter estimators with the proposed GEE method for a marginal cumulative probit model appear to be less biased and more efficient than those with the independence "working" model, especially for studies having time-varying covariates and strong correlation.

The prognostic value of electroencephalography in epilepsy: a long-term follow-up study.

Predicting the evolution of epilepsy is of obvious importance for patients and their families. Value of electroencephalography (EEG) is extensively used in the diagnosis of epilepsy yet its role as a prognostication method remains unclear. The aim of the present retrospective study is to investigate the relationship between serial EEG recordings and long-term clinical and social outcomes in a cohort of patients with epilepsy. Thirty-nine epileptic patients were monitored clinically and with repeat EEG recordings for more than 15 years. All patients who initially had epileptiform discharges ended up with poor or moderate seizure control whereas more than half of the patients with normal initial recordings had good clinical outcomes and satisfactory social adjustment. Deterioration of the recordings over time was associated with unfavourable results in a significant proportion of patients (90%), while stable or improved EEG findings predicted a favourable outcome. It is concluded that serial EEG recordings can be used in the prognostic evaluation of epilepsy.

Hospitalization rates for cholelithiasis and acute cholecystitis doubled for the aged population in Greece over the past 30 years.

OBJECTIVE: Gallbladder disease is becoming increasingly prevalent in Western countries and is a common cause of hospitalization. The objective of this study was to determine time trends in cholelithiasis and acute cholecystitis for hospitalization and disease case fatality in Greece between 1970 and 1998. MATERIAL AND METHODS: Data were obtained from the Annual Bulletin for the Social Welfare and Health Statistics of the National Statistics Service of Greece. Percentage changes in time trends were estimated by comparing the median values of the initial (1970-78) to the last (1989-98) 10-year study period for cholelithiasis and acute cholecystitis at discharge and for all deaths attributed to the disease. RESULTS: Over the study period, age-standardized hospitalization rates for cholelithiasis increased. The median hospitalization rate between the initial and last (178 and 258 per 100,000 of the population, respectively) 10-year study period increased by 44.7%, but peaked to 70.1% and 208.3% for the 70-79 and >80 years age groups, respectively. Case fatality rate declined by 56.8% and the median value was 0.24 per 100 patients hospitalized during the last 10-year period. CONCLUSIONS: Hospitalization rates for cholelithiasis and/or acute cholecystitis increased by 45%, and doubled for elderly patients, while the case fatality rate of the disease halved in Greece over the past 30 years.

Valproate-induced eosinophilia in children with epilepsy: role of interleukin-5.

Interleukin-5 contributes both in eosinophilopoiesis and neural development. Serum interleukin-5 levels were measured with enzyme-linked immunosorbent assay technique in 68 children with epilepsy receiving sodium valproate monotherapy and compared with the levels of 60 healthy controls and 14 children with epilepsy receiving carbamazepine. Eosinophilia was observed in 35.3% of children receiving valproate. Interleukin-5 in valproate users was significantly higher compared with children receiving carbamazepine and controls. Valproate users who exhibited eosinophilia had higher interleukin-5 levels compared with those without eosinophilia. However, the interleukin-5 level was also elevated, although to a lesser degree, in children without eosinophilia. The majority of valproate responders had high interleukin-5 levels. A positive correlation between interleukin-5 levels and the eosinophil count was also noted. We postulate that valproate contributes to the pathogenesis of eosinophilia, probably inducing interleukin-5 production. The finding that serum interleukin-5 was significantly elevated in valproate responders and even in valproate users without eosinophilia suggests that the increase in interleukin-5 might represent one of valproate's antiepileptic mechanisms.

Weather conditions and sudden sensorineural hearing loss.

BACKGROUND: Climatic or meteorological condition changes have been implicated in the pathogenesis of Idiopathic Sudden Sensorineural Hearing Loss (ISSHL). We investigated the seasonal distribution of ISSHL and evaluated the influence of meteorological parameters (such as temperature, humidity, and atmospheric pressure), their variation and covariation on the incidence of the disease. METHODS: A total of 82 cases of ISSHL, admitted to our department over a five-year period, were enrolled in the study. Seasonal distribution of the disease was investigated by dividing the year in four seasons. Meteorological data included daily values of 13 distinct parameters recorded at the meteorological station of the University of Ioannina during this period. A relationship between each meteorological variable and the incidence of ISSHL was investigated by applying (chi2) test on data from 13 contingency tables as well as by using logistic regression and t-test approaches. In addition, the influence of different weather types on the incidence of ISSHL was investigated using Cluster Analysis in order to create eight clusters (weather types) characteristic for the prefecture of Ioannina. RESULTS: The results of the study could not indicate any seasonal distribution of the disease. The incidence of ISSHL could not be significantly correlated either to any distinct meteorological parameter or to any specific weather type. CONCLUSIONS: Meteorological conditions, such as those dominating in the Northwestern Greece, and/or their changes, have no proven effect on the incidence of ISSHL.