Covariance Research Articles

Dioxins released from incineration plants and mortality from major diseases: an analysis of statistical data by municipalities.

The aim of this study is to examine the relation between mortality and the existence of incineration plants and dioxin released from the plants in 590 municipalities across Japan. The concentration of dioxins in emissions from incinerators, the amount of dioxins per population, the cumulative amount of dioxins, and the cumulative amount per land area were used as dioxin-related municipal indices. Age-adjusted mortality rates from all causes and five major disease categories by municipality in 1995 were used as health indices. The relation was examined using t-test, analysis of covariance (ANCOVA), correlation coefficients and multiple linear regression analysis, considering the effects of cities' socioeconomic conditions. Although municipalities with plants had significantly higher mortality from female stroke and lower mortality from male cancer at all site and lung than municipalities without plants, these differences were not significant in ANCOVA with socioeconomic indicators. The significant relation between mortality and dioxin indices in correlation coefficient was ruled out when the socioeconomic conditions were adjusted in multiple regression analysis. This study did not show the statistical relation between increased mortality from major causes and the existence of incineration plants and dioxins from the plants at the municipal level.

Characteristics or Covariance: Further Evidence

Characteristics or Covariance: Further Evidence

Chessboard Distributions and Random Vectors with Specified Marginals and Covariance Matrix

There is a growing need for the ability to specify and generate correlated random variables as primitive inputs to stochastic models.Moti vated by this need, several authors have explored the gener...

Credit Enhancement and Loan Default Risk Premiums

AbstractUsing contingent claims analysis, we study the impact of private guarantees on the default risk premiums or credit spreads of discount loans. Specifically, we analyze the reduction of the default risk premium on a new junior loan by obtaining the numerical estimates under a stochastic interest rate. We demonstrate how the value of credit enhancement relates to the profitability and size of the new junior loan, as well as the leverage, asset risk, and debt seniority of the borrowing firm and the private insurer. The main results show that (a) for the new junior loan, although the benefits of financial insurance are substantial with an AAA‐rated private insurer, in general, default risk premiums can only be reduced to a minute amount; and (b) even with complete insurance coverage from an AAA‐rated private insurer, loan issues command default risk premiums that reflect not only the intrinsic values and risks of the insured and the insurer, but also their covariance.RésuméNous examinons l'impact des garanties financières privées sur la structure de risque des taux d'intérêt des prêts escomptés en utilisant l'approche d'évaluation de Brennan (1979) et de Stapleton et Subrahmanyam (1984) qui n'impose pas la condition de perte et de gain nul sur les créanciers. Nous étudions également la réduction (ou augmentation) des primes de risque de défaut des dettes sous le régime de taux d'intérêt stochastique. Pour obtenir des résultats de statique comparée, des simulations numériques ont été entreprises. Les résultats confirment les évidences empiriques provenant du marché d'assurance (et de rehaussement de crédit) des obligations. Nous trouvons que les primes de défaut ne peuvent être éliminées complètement par des endosseurs privés donc vulnérables.

Existence of the uniformly minimum risk equivariant estimators of parameters in a class of normal linear models

In this paper, we study the existence of the uniformly minimum risk equivariant (UMRE) estimators of parameters in a class of normal linear models, which include the normal variance components model, the growth curve model, the extended growth curve model, and the seemingly unrelated regression equations model, and so on. The necessary and sufficient conditions are given for the existence of UMRE estimators of the estimable linear functions of regression coefficients, the covariance matrix V and (tr V ) α , where α > 0 is known, in the models under an affine group of transformations for quadratic losses and matrix losses, respectively. Under the (extended) growth curve model and the seemingly unrelated regression equations model, the conclusions given in literature for estimating regression coefficients can be derived by applying the general results in this paper, and the sufficient conditions for non-existence of UMRE estimators of V and tr( V ) are expanded to be necessary and sufficient conditions. In addition, the necessary and sufficient conditions that there exist UMRE estimators of parameters in the variance components model are obtained for the first time.

Comparison of two estimators of mean function in LDA of spatially correlated Gaussian data

Abstract The problem of linear discriminant analysis of an observation of Gaussian random field into one of two populations is considered. In this paper we analyze the performance of the plug‐in linear discriminant function, when unknown means are estimated from the training samples. The generalized least squares and the ordinary least squares estimators are used. Obtained asymptotic expansions for the expected error rate are compared numerically in the case of spherical models for population covariances.

Comparison of ML and OLS Estimators in Discriminant Analysis of Spatially Correlated Observations

The problem of supervised classification of the realisation of the stationary univariate Gaussian random field into one of two populations with different means and factorised covariance matrices is considered. Unknown means and the common covariance matrix of the feature vector components are estimated from spatially correlated training samples assuming spatial correlation to be known. For the estimation of unknown parameters two methods, namely, maximum likelihood and ordinary least squares are used. The performance of the plug-in discriminant functions is evaluated by the asymptotic expansion of the misclassification error. A set of numerical calculations is done for the spherical spatial correlation function.

Association of work status and mental well-being in new mothers.

The present study was to consider the relationship between work status and mental well-being of women at six weeks postpartum. One hundred and eighty-eight employed mothers and 82 unemployed mothers were recruited from the Kaohsiung city area in southern Taiwan to participate in this study. Five instruments were used to collect data: the demographic data form, Cohen's perceived stress scale, Cohen's interpersonal support evaluation list, Coopersmith's self-esteem inventory, and the Beck depression inventory. In results, unemployed mothers were younger, had fewer years of education, and lower socioeconomic status than employed mothers. To adjust for these differences in group characteristics, one-way analysis of covariance (ANCOVA) was performed to determine the role of work on mental health factors. Unemployed mothers were found to be at significantly increased risk for depression in terms of prevalence and severity. They also showed significantly greater stress, reduced social support and lowered self-esteem. That employment is mentally beneficial for post-partum women may be due to increased financial resources and provision of additional stress release outlets, social support resources and opportunities for affirmation of personal worth. Since this study is cross-sectional, some reasonable alternative causal explanations for these data were also discussed.

Covariances

Covariances

Modifications to KB2D program in GSLIB to allow use of tabulated covariances calculated with fast Fourier transform method

Modifications to KB2D program in GSLIB to allow use of tabulated covariances calculated with fast Fourier transform method

The effect of temperature and saturation deficit on mortality in populations of male Glossina m. morsitans (Diptera: Glossinidae) in Zimbabwe and Tanzania.

The methods of Bailey and of Jolly and Seber were used to provide maximum likelihood estimates of population parameters for Jackson's classical mark-recapture experiments on males of the tsetse fly Glossina m. morsitans Westwood. These were compared with Jolly-Seber (J-S) estimates for the same fly from more recent work on Antelope Island, Lake Kariba, Zimbabwe. The Bailey estimates of birth and death rates and total population size had markedly lower variances than Jackson's originals. Both sets of estimates provided moving averages over 6-week periods, whereas the Jolly-Seber analysis provided independent weekly estimates and their variance is consequently higher. Saturation deficit and maximum temperature (Tmax) accounted for 11 and 16% respectively of the variance in independent 4-week means of the weekly J-S survival probabilities. Analysis of covariance, carried out on a joint data set of smoothed J-S estimates of the survival probability in Tanzania and Zimbabwe, showed a significant effect of Tmax on survival. When this effect was removed, the survival probability in the Tanzania studies was found to be 8% lower than on Antelope Island. The two effects accounted for 50% of the variance in the joint data. When saturation deficit was substituted for Tmax, regression only accounted for 35% of the variance. If saturation deficit is important in determining tsetse survival, it must act on stages other than the post-teneral adult. Given the continuous increase in mortality, even at moderate temperatures, it is hard to envisage a direct effect of Tmax. There may be an indirect effect, however, via the number of hunger-related deaths resulting from the increase in the feeding rate with increasing temperature.

Analisi di stabilità: modelli d'effetti misti

In the paper the stability analysis of a pharmaceutical compound is presented. The purpouse of a stability analysis, is to determin the period of time within wich the compound conserve its initial characetris. At each time point an evaluation a previous trend analysis is caried out. The underlining trend is supposed to be linear or reduced to be linear following the equation C = a+b t, where C is the level of active content. The determination of such trend allows the estimation of the content at varous time points, and to check if the level is greater than a fixed value (the specification). This value represent theminimal condition the copmound must fulfill.,that is:ICH and FDA guide-lines recommend that the lower confidence limit is reported too. If such limit at a time point si greater than the specification,then at such time the specification is fulfilled.Such analysis is performed under the condition of classical regression model. An alternative approach is represented by the use of a mixed model in which the batch effect is regarded as a random effect. This approach appear, from a theoretical point of view, more appealing, since it does not reguest to adopt the step wise procedure seen below. The difference between batch is a variability factor whose effect the variability of the observed result. Such variability can be modelled using a suitable covariance matrix.

Pressure-potential-temperature covariance in convection with rotation

Pressure-potential-temperature covariance in convection with rotation

Age and the subjective experience of shiftwork.

The objective of this study was to examine age related effects of shiftwork albeit difficult to tease apart the natural effects of aging, and lifestyle or behaviour, or job done, over time and the shifts a person works. This is an issue of concern because the numbers of shiftworkers over 45 are increasing. Participants were 306 police officers who had worked a new rota for approximately 6 months. Three age groups were compared (1 = 20-32.9, 2 = 33-39.9, 3 = 40+) using a range of shiftwork-related measures and multivariate analysis of covariance (controlling for shiftwork experience and other individual differences). Younger officers tended to report significantly better attitudes towards their shiftwork, better adjustment to night-bound shifts, greater job satisfaction and organisational commitment, lower fatigue and longer sleep durations. Older shiftworkers reported significantly higher morningness and lower sleep need than the younger officers. This concurred with existing research that implicates such variables in the mechanism(s) involved in age-related tolerance to shiftwork. It was also evident that the older group tended to resort to greater caffeine intake on all shifts. The findings offer tentative support for the position that age can be linked to depleted shiftwork tolerance but the issue of establishing the relative impacts of aging, lifestyle, behaviour, work type and the rota worked remains to be a challenge.

THE USE OF MIXED EFFECTS ANCOVA TO CHARACTERIZE VEHICLE EMISSION PROFILES

A mixed effects analysis of covariance model to characterize mileage dependent emissions profiles for any given group of vehicles having a common model design is used in this paper. These types of evaluations are used by the U.S. Environmental Protection Agency to certify whether or not new models conform to existing emissions standards. The statistical models introduced describe both the average emissions profile for a group of vehicles as well as an accounting for individual vehicle variability within the group. Realistic confidence bounds for an average emissions deterioration profile within a given group can also be provided to allow accurate emissions comparison of multiple groups. Sample of emissions data is presented for two types of vehicles: natural gas Dodge Ram vans and gasoline Dodge Ram vans (all from the 1992-94 model years). Additionally, the population profile for nonmethane hydrocarbons is explored.

Estimating Bottom Stress in Tidal Boundary Layer from Acoustic Doppler Velocimeter Data

Bed stresses in the bottom boundary layer of the York River estuary, Virginia, were estimated from three-dimensional near-bottom velocities measured by Acoustic Doppler Velocimeters (ADVs) and also by a profiling array of electromagnetic current meters. By assuming the measurements were made in a constant stress layer, four methods of stress estimation were evaluated using ADVs: direct covariance (COV) measurement, turbulent kinetic energy, inertial dissipation utilizing the Kolmogorov spectrum, and log profile. The four methods yielded similar estimates of frictional velocity (U*) based on ADV output from both 14 cm and 44 cm above bed. All eight estimates of average U* were consistent with the overall mean of 1.10 cm/s to within the 95% confidence interval for individual burst estimates. The COV method worked slightly better nearer the bed, possibly because of the sensitivity of COV to the upper limit of the constant stress layer. The inertial dissipation method performed marginally well at 14 cm above bed, likely because of sediment induced stratification and insufficient separation of turbulent production and dissipation scales. The log profile method was the most variable and appeared most sensitive to stratification and to the thickness of the constant stress layer. The turbulent kinetic energy method was the most consistent at both heights and appears most promising for further development. Results encourage future use of the ADV in estuarine environments but also favor the simultaneous use of several methods to estimate bottom stress.

Mesoscopic dynamics of chaos in chemical Lorenz model

The mesoscopic dynamics of the chemical Lorenz system has been examined within the framework of master equation description by means of ensemble stochastic simulations. The time evolution of the bin frequency, which approximates the probability of the master equation, has been checked in dynamic regimes of fixed points, limit cycles and chaos. The variances and covariances between different species are also calculated and compared. Results presented suggest a picture of mesoscopic dynamics beyond the usual deterministic description.

Two-stage fractionation history of the alkali basalt-trachyte series of Sete Cidades volcano (São Miguel Island, Azores).

A comprehensive data set of mineral and whole-rock major element compositions of the Na-alkaline lavas and pumices erupted by the Sete Cidades volcano (Sao Miguel Island, Azores) is here presented. Mineralogy and geochemistry of the Sete Cidades extrusives indicate a low-pressure fractional crystallization, at relatively high fO2, as the main magmatic process generating the volcanic suite, which is mostly made up of basaltic-hawaiitic and trachytic rocks; very few mugearites are known on Sete Cidades emphasizing the possibility that residual liquids were able to leave the hawaiitic crystal mush only when the density had been lowered by compositional change or volatile exsolution ( i.e. at the trachytic stage). We mainly show how compositional variations within each group of silicates (and non-silicate) and the major-trace element covariances in the mineral structures through the alkali basalt-trachyte series are highly dependent on the sequence of crystallization and the correspondent magmatic environment (temperature, pressure, fO 2 ). Relatively primitive, slightly ne - normative basalts with MgO up to 14 % were tapped through flank eruptions indicating they were not held at any crustal levels, with rapid ascent through the plumbing system. Some of these basalts were held close to the Moho where they evolved by wehrlite fractionation to produce slightly hy - normative hawaiites with less than 7 % MgO. Slightly evolved basalts or hawaiitic magmas leaving the deep crustal reservoir were either erupted or were trapped in high level magma chambers to fractionate through towards metaluminous, q - + an - normative two-feldspar trachytes and thence to slightly peralkaline, one-feldspar, q - + ac - normative trachytes. Evidence of this liquid line of descent is also constrained by the hornblendite-kaersutite gabbro-diorite shallow plutonic roots of the volcano. Geothermobarometric and fO 2 calculations, performed on equilibrated pair of minerals (or mineral/liquid) generally agree with the proposed two-stage fractionation history of the Sete Cidades Na-alkaline magmas occurred within the relatively thick Azorean oceanic crust.

Covarianza fra media campionaria e differenza media: aspetti formali e relazioni con l’asimmetria

In a recent work Polisicchio and Zenga (1996) deduced a simple formula for the covariance betwen sample mean and (sample) mean difference in case of finite population. Studying the joint distribution of sample mean and (sample) mean difference derived from three simple discrete populations, the same authors observed a concordance between the sign of this covariance and the sense of asymmetry of the populations in case. In this work simple and equivalent formulas of the covariance between sample mean and (sample) mean difference will be deduced in the continuos case. These formulas will then be applied to the uniform, exponential, Pareto and “inverse” Pareto random variables. These applications show the same relationship between the asymmetry and the sign of the covariance: Then, it will be shown that monotonicity of point asymmetries is relevant to check the sign of the above mentioned covariance, both for continuos and discrete case.

Diffusion and Perfusion MRI in Predicting Final Infarct Volume: A Study of 81 Patients with Acute Stroke

P25 Purpose: To assess the utility of diffusion weighted imaging, cerebral blood volume, cerebral blood flow and mean transit time mapping in predicting final infarct volume in 81 patients with acute ischemic stroke. Methods: DWI, CBV, CBF and MTT images were obtained in 81 patients within 53 hours of stroke onset. Follow-up CT or T2 weighted MR images were obtained at 1 day to 4 months. Ischemic region volumes were measured on all images. An analysis of covariance with the variables of age, sex, treatment, time from stroke onset to imaging, and lesion type was performed. Linear regressions of DWI, CBV, CBF and MTT versus final infarct volume were obtained. A mismatch was determined if there was greater than 20% difference in volume between the diffusion and perfusion images. Results: Analysis of covariance demonstrated that DWI best predicts final infarct volume and that CBV alone of the other variables significantly improves the DWI prediction of final infarct volume. Linear regression analysis yielded an R 2 of 0.90, slope of 1.24 for DWI versus follow-up, R 2 of 0.84, slope of 1.22 for CBV versus follow-up, R 2 of 0.37, slope of 0.44 for CBF versus follow-up and R 2 of 0.25, slope of 0.33 for MTT versus follow-up. 13/81 patients had a DWI - CBV mismatch with mean lesion growth of 121 % while 68/81 patients had a DWI - CBV match with mean lesion growth of 15%. 36/81 had a DWI - CBF mismatch with mean lesion growth of 56% while 45/81 had a DWI - CBF match with mean lesion growth of 13%. 43/81 had a DWI - MTT mismatch with mean lesion growth of 47%. 38/81 had a DWI - MTT match with mean lesion growth of 16%. Conclusions: Both DWI and CBV are very good predictors of final infarct volume. CBF and MTT maps identify tissue at risk of infarction not identified on DWI or CBV maps. Since this tissue does not always infarct, these maps greatly overestimate final infarct size.The identification of a DWI - CBV, DWI - CBF or DWI - MTT mismatch predicts much more lesion growth compared with a diffusion perfusion match. This is most dramatic for DWI - CBV mismatches. This information may be valuable in the assessment of new therapeutic strategies.