Supply-side risk adjustment and outlier payment policy

In most health care systems where a prospective payment system is implemented, an outlier payment is used to cover the hospitals' unusually high costs. When the hospital chooses its cost reduction effort before observing a patient's severity, we show that the best outlier payment is based on the realized cost when the hospital exerts the first best level of effort, for any level of severity. [Authors]

Adverse selection, moral hazard, and outlier payment policy

In this article, we analyze the rationale for introducing outlier payments into a prospective payment system for hospitals under adverse selection and moral hazard. The payer has only two instruments: a fixed price for patients whose treatment cost is below a threshold and a cost-sharing rule for outlier patients. We show that a fixed-price policy is optimal when the hospital is sufficiently benevolent. When the hospital is weakly benevolent, a mixed policy solving a trade-off between rent extraction, efficiency, and dumping deterrence must be preferred. We show how the optimal combination of fixed price and partially cost-based payment depends on the degree of benevolence of the hospital, the social cost of public funds, and the distribution of patients severity. [Authors]

Modular framework for outlier detection

Outlier detection is an important form of data analysis because outliers in several cases contain the interesting and important pieces of information. In the recent years, many different outlier detection algorithms have been devised for finding different kinds of outliers in varying contexts and environments. Some effort has been put to study how to effectively combine different outlier detection methods. The combination of outlier detection algorithms as an ensemble was studied in this thesis by designing a modular framework for outlier detection, which combines arbitrary outlier detection techniques. This work resulted in an example implementation of the framework. Outlier detection capability of the ensemble method was validated using datasets and methods found in outlier detection research. The framework achieved better results than the individual outlier algorithms. Future research includes how to handle large datasets effectively and the possibilities for real-time outlier monitoring.

Detection of frailty in Weibull lifetime data using Outlier tests

Heterogeneity in lifetime data may be modelled by multiplying an individual's hazard by an unobserved frailty. We test for the presence of frailty of this kind in univariate and bivariate data with Weibull distributed lifetimes, using statistics based on the ordered Cox-Snell residuals from the null model of no frailty. The form of the statistics is suggested by outlier testing in the gamma distribution. We find through simulation that the sum of the k largest or k smallest order statistics, for suitably chosen k , provides a powerful test when the frailty distribution is assumed to be gamma or positive stable, respectively. We provide recommended values of k for sample sizes up to 100 and simple formulae for estimated critical values for tests at the 5% level.

Combined bias and outlier identification in dynamic data reconciliation

Measured process data normally contain inaccuracies because the measurements are obtained using imperfect instruments. As well as random errors one can expect systematic bias caused by miscalibrated instruments or outliers caused by process peaks such as sudden power fluctuations. Data reconciliation is the adjustment of a set of process data based on a model of the process so that the derived estimates conform to natural laws. In this paper, techniques for the detection and identification of both systematic bias and outliers in dynamic process data are presented. A novel technique for the detection and identification of systematic bias is formulated and presented. The problem of detection, identification and elimination of outliers is also treated using a modified version of a previously available clustering technique. These techniques are also combined to provide a global dynamic data reconciliation (DDR) strategy. The algorithms presented are tested in isolation and in combination using dynamic simulations of two continuous stirred tank reactors (CSTR).

Legal outlier, again? U.S. felon suffrage: comparative and international human rights perspectives

The judiciousness of American felon suffrage policies has long been the subject of scholarly debate, not least due to the large number of affected Americans: an estimated 5.3 million citizens are ineligible to vote as a result of a criminal conviction. This article offers comparative law and international human rights perspectives and aims to make two main contributions to the American and global discourse. After an introduction in Part I, Part II offers comparative law perspectives on challenges to disenfranchisement legislation, juxtaposing U.S. case law against recent judgments rendered by courts in Canada, South Africa, Australia, and by the European Court of Human Rights. The article submits that owing to its unique constitutional stipulations, as well as to a general reluctance to engage foreign legal sources, U.S. jurisprudence lags behind an emerging global jurisprudential trend that increasingly views convicts’ disenfranchisement as a suspect practice and subjects it to judicial review. This transnational judicial discourse follows a democratic paradigm and adopts a “residual liberty” approach to criminal justice that considers convicts to be rights-holders. The discourse rejects regulatory justifications for convicts’ disenfranchisement, and instead sees disenfranchisement as a penal measure. In order to determine its suitability as a punishment, the adverse effects of disenfranchisement are weighed against its purported social benefits, using balancing or proportionality review. Part III analyzes the international human rights treaty regime. It assesses, in particular, Article 25 of the International Covenant on Civil and Political Rights (“ICCPR”), which proclaims that “every citizen” has a right to vote without “unreasonable restrictions.” The analysis concludes that the phrase “unreasonable restrictions” is generally interpreted in a manner which tolerates certain forms of disenfranchisement, whereas other forms (such as life disenfranchisement) may be incompatible with treaty obligations. This article submits that disenfranchisement is a normatively flawed punishment. It fails to treat convicts as politically-equal community members, degrades them, and causes them grave harms both as individuals and as members of social groups. These adverse effects outweigh the purported social benefits of disenfranchisement. Furthermore, as a core component of the right to vote, voter eligibility should cease to be subjected to balancing or proportionality review. The presumed facilitative nature of the right to vote makes suffrage less susceptible to deference-based objections regarding the judicial review of legislation, as well as to cultural relativity objections to further the international standardization of human rights obligations. In view of this, this article proposes the adoption of a new optional protocol to the ICCPR proscribing convicts’ disenfranchisement. The article draws analogies between the proposed protocol and the ICCPR’s “Optional Protocol Aiming at the Abolition of the Death Penalty.” If adopted, the proposed protocol would strengthen the current trajectory towards expanding convicts’ suffrage that emanates from the invigorated transnational judicial discourse.

Bayesian outlier analysis in binary regression

We propose alternative approaches to analyze residuals in binary regression models based on random effect components. Our preferred model does not depend upon any tuning parameter, being completely automatic. Although the focus is mainly on accommodation of outliers, the proposed methodology is also able to detect them. Our approach consists of evaluating the posterior distribution of random effects included in the linear predictor. The evaluation of the posterior distributions of interest involves cumbersome integration, which is easily dealt with through stochastic simulation methods. We also discuss different specifications of prior distributions for the random effects. The potential of these strategies is compared in a real data set. The main finding is that the inclusion of extra variability accommodates the outliers, improving the adjustment of the model substantially, besides correctly indicating the possible outliers.

Morphological Homogeneity of Neurons: Searching for Outlier Neuronal Cells

We report a morphology-based approach for the automatic identification of outlier neurons, as well as its application to the NeuroMorpho.org database, with more than 5,000 neurons. Each neuron in a given analysis is represented by a feature vector composed of 20 measurements, which are then projected into a two-dimensional space by applying principal component analysis. Bivariate kernel density estimation is then used to obtain the probability distribution for the group of cells, so that the cells with highest probabilities are understood as archetypes while those with the smallest probabilities are classified as outliers. The potential of the methodology is illustrated in several cases involving uniform cell types as well as cell types for specific animal species. The results provide insights regarding the distribution of cells, yielding single and multi-variate clusters, and they suggest that outlier cells tend to be more planar and tortuous. The proposed methodology can be used in several situations involving one or more categories of cells, as well as for detection of new categories and possible artifacts.

Algoritmi per la scoperta di outlier in sistemi di calcolo ad altissime prestazioni

In questa tesi vengono analizzati gli algoritmi DistributedSolvingSet e LazyDistributedSolvingSet e verranno mostrati dei risultati sperimentali relativi al secondo.

Healthcare Outlier Payment Costs

The purpose of this project is to determine the cost of healthcare per individual depending on the amount of care needed.

Healthcare Costs: How Much Could a Hospital Make on Outlier Patients in Montana?

This poster illustrates hospital cost for outlier patients in Montana.

Outlier detection with partial information:Application to emergency mapping

This paper, addresses the problem of novelty detection in the case that the observed data is a mixture of a known 'background' process contaminated with an unknown other process, which generates the outliers, or novel observations. The framework we describe here is quite general, employing univariate classification with incomplete information, based on knowledge of the distribution (the 'probability density function', 'pdf') of the data generated by the 'background' process. The relative proportion of this 'background' component (the 'prior' 'background' 'probability), the 'pdf' and the 'prior' probabilities of all other components are all assumed unknown. The main contribution is a new classification scheme that identifies the maximum proportion of observed data following the known 'background' distribution. The method exploits the Kolmogorov-Smirnov test to estimate the proportions, and afterwards data are Bayes optimally separated. Results, demonstrated with synthetic data, show that this approach can produce more reliable results than a standard novelty detection scheme. The classification algorithm is then applied to the problem of identifying outliers in the SIC2004 data set, in order to detect the radioactive release simulated in the 'oker' data set. We propose this method as a reliable means of novelty detection in the emergency situation which can also be used to identify outliers prior to the application of a more general automatic mapping algorithm. © Springer-Verlag 2007.

Outlier detection in scatterometer data:Neural network approaches

Satellite-borne scatterometers are used to measure backscattered micro-wave radiation from the ocean surface. This data may be used to infer surface wind vectors where no direct measurements exist. Inherent in this data are outliers owing to aberrations on the water surface and measurement errors within the equipment. We present two techniques for identifying outliers using neural networks; the outliers may then be removed to improve models derived from the data. Firstly the generative topographic mapping (GTM) is used to create a probability density model; data with low probability under the model may be classed as outliers. In the second part of the paper, a sensor model with input-dependent noise is used and outliers are identified based on their probability under this model. GTM was successfully modified to incorporate prior knowledge of the shape of the observation manifold; however, GTM could not learn the double skinned nature of the observation manifold. To learn this double skinned manifold necessitated the use of a sensor model which imposes strong constraints on the mapping. The results using GTM with a fixed noise level suggested the noise level may vary as a function of wind speed. This was confirmed by experiments using a sensor model with input-dependent noise, where the variation in noise is most sensitive to the wind speed input. Both models successfully identified gross outliers with the largest differences between models occurring at low wind speeds. © 2003 Elsevier Science Ltd. All rights reserved.