Ratio tests under limiting normality

We propose a class of ratio tests that is applicable whenever a cumulation (of transformed) data is asymptotically normal upon appropriate normalization. The Karhunen–Loève theorem is employed to compute weighted averages. The test statistics are ratios of quadratic forms of these averages and hence scale-invariant, also called self-normalizing: The scaling parameter cancels asymptotically. Limiting distributions are obtained. Critical values and asymptotic local power functions can be calculated by standard numerical means. The ratio tests are directed against local alternatives and turn out to be almost as powerful as optimal competitors, without being plagued by nuisance parameters at the same time. Also in finite samples they perform well relative to self-normalizing competitors.     

Analysis of clustered spatially correlated binary data using autologistic model and Bayesian method with an application to dental caries of 3–5-year-old children

The autologistic model, first introduced by Besag, is a popular tool for analyzing binary data in spatial lattices. However, no investigation was found to consider modeling of binary data clustered in uncorrelated lattices. Owing to spatial dependency of responses, the exact likelihood estimation of parameters is not possible. For circumventing this difficulty, many studies have been designed to approximate the likelihood and the related partition function of the model. So, the traditional and Bayesian estimation methods based on the likelihood function are often time-consuming and require heavy computations and recursive techniques. Some investigators have introduced and implemented data augmentation and latent variable model to reduce computational complications in parameter estimation. In this work, the spatially correlated binary data distributed in uncorrelated lattices were modeled using autologistic regression, a Bayesian inference was developed with contribution of data augmentation and the proposed models were applied to caries experiences of deciduous dents.     

Development of a carpal tunnel syndrome screening method using structured interviews and vibrotactile testing

Carpal tunnel syndrome (CTS) is a debilitating and expensive health problem. An inexpensive screening method that would differentiate between people who do not have CTS and those that may have CTS would be useful. The screening methodology investigated here had two phases: a structured interview and provocative vibrotactile testing (VT). The control group (n = 36) was composed of asymptomatic college students and faculty, the case group was composed of patients currently visiting an occupational medicine clinic for symptoms consistent with CTS. The case group was subdivided into positive and negative for nerve conduction latency, NCL+ (n = 21) and NCL- (n = 13), respectively. Using a scored, structured interview, 33 of the controls and none of the symptomatic cases were identified as non-CTS. The results from the provocative flexion VT indicated that if the difference between the age corrected baseline and the threshold at 15 minutes is 15 microm or more, the subject was likely to be NCL+ (odds ratio 12.6, 95% CI 3.8 to 41.8). Further research may improve this screening methodology to not only determine whether or not a person has CTS, but also to determine the level of median nerve impingement or damage.     

Supply chain configuration for diffusion of new products: An integrated optimization approach

We develop an integrated/hybrid optimization model for configuring new products’ supply chains while explicitly considering the impact of demand dynamics during new products’ diffusion. The hybrid model simultaneously determines optimal production/sales plan and supply chain configuration. The production and sales plan provides decisions on the optimal timing to launch a new product, as well as the production and sales quantity in each planning period. The supply chain configuration provides optimal selection of options and safety stock level kept at each supply chain function. Extensive computational experiments on randomly generated testbed problems indicate that the hybrid modeling and solution approach significantly outperforms non-hybrid alternative modeling and solution approaches under various diffusion and supply chain topologies. We provide insights on optimal production/sales plan and supply chain configuration for new products during their diffusion process. Also, managerial implications relevant to effectiveness of the hybrid approach are discussed.     

Modified maximum likelihood estimator for the mixing distribution in a finite mixture

Using the likelihood equations, a method based on the generalized inverse of matrices is proposed to derive closed-form estimates for the mixing proportions in a finite mixture, when the component distributions are known.     

On detecting outliers in the Pareto distribution

In this paper, we introduce two new statistics for detecting outliers in the Pareto distribution. These new statistics are the extension of the statistics for detecting outliers in exponential and gamma distributions. In fact, we compare the power of our test statistics with the other statistics and select the best test statistic for detecting outliers in the Pareto distribution. Finally, numerical examples of different insurance claims are used to see the performance of the test.     

A comparative study of series arima/mlp hybrid models for stock price forecasting

ABSTRACT

Series hybrid models are one of the most widely-used hybrid models that in which a time series is assumed to be composed of two linear and nonlinear components. In this paper, the performance of two types of these hybrid models is evaluated for predicting stock prices in order to introduce the more reliable series hybrid model. For this purpose, ARIMA and MLPs are elected for constructing series hybrid models. Empirical results for forecasting three benchmark data sets indicate that despite of more popularity of the conventional ARIMA-ANN model, the ANN-ARIMA hybrid model can overall achieved more accurate results.     

Order statistics and their concomitants from multivariate normal mean–variance mixture distributions with application to Swiss Markets Data

In this article, by considering a multivariate normal mean–variance mixture distribution, we derive the exact joint distribution of linear combinations of order statistics and their concomitants. From this general result, we then deduce the exact marginal and conditional distributions of order statistics and their concomitants arising from this distribution. We finally illustrate the usefulness of these results by using a Swiss markets dataset.     

Institutionalized norms of conducting research and social realities: A research synthesis of empirical works from 1983 to 2002

Based on a systematic review of the last 20 years of empirical research grounded in institutional theory, we identify some of the main norms of conducting research in this literature. The level of institutions, the formal/informal institutional pillars and the direction of effects are the foundation of these norms addressed by researchers in the last two decades. This review indicates that empirical research is well behind changes in social realities. This may be related to both the institutionalization process that takes place in any academic research and to the suggested difficulty that scholars find in moving away from widely accepted research models and practices, given the context within which they evolve. It is also concluded that local/national regulative institutions are giving up their position to more global normative and cognitive organizational field institutions. As the business environment become more global, giving more importance to transnational and informal institutions will be more crucial in institutional analysis of organizations.