On the distribution of rin samples from the mixtures of bivariate normal populations

The distributions of some transformations of the sample correlation coefficient r are studied here, when the parent population is a mixture of two standard bivariate normals. The behavior of these transformations is assessed through the first four standard moments. It is shown that there is a close relationship between the behavior of the transformed variables and the lack of normality as evinced by the 'kurtosis' defined in the bivariate population     

对印投资的政治风险及其法律应对措施

印度独立后,总体上对外资持欢迎态度,1991年实行自由化改革以来尤其如此。印度的政治制度、法律制度和经济制度有助于避免大规模政治风险的发生,但国有化和征收风险、汇兑风险、政府违约风险、战争和内乱风险在一定范围内仍然存在。外国投资者对印度投资,有必要采取适当的法律应对措施,以防止和消除政治风险,进而确保投资利润和目标的实现。     

Bernstein's languages of description: Some generative principles

There are numerous ways of displaying Likert‐type scales but only a few investigators have investigated these differences systematically. In this study we report the results that we found when we compared four different layouts: scales that went numerically from ‘0’ to ‘10’, or from ‘10’ to ‘0’, and scales that went verbally from ‘clear’ to ‘unclear’, or ‘unclear’ to ‘clear’. Over 450 participants rated each of seven aspects of a structured abstract in a web‐based study, with each one using only one of the four scale formats listed above. The resulting data showed that the scale ‘Clear – 10 … 0 – Unclear’ consistently led to significantly higher ratings in all seven cases. Such findings have implications for the design of Likert‐type scales and for the data that are gathered from them.     

On choosing between fixed and random block effects in some no-interaction models

The purpose of this article is to strengthen the understanding of the relationship between a fixed-blocks and random-blocks analysis in models that do not include interactions between treatments and blocks. Treating the block effects as random has been recommended in the literature for balanced incomplete block designs (BIBD) because it results in smaller variances of treatment contrasts. This reduction in variance is large if the block-to-block variation relative to the total variation is small. However, this analysis is also more complicated because it results in a subjective interpretation of results if the block variance component is non-positive. The probability of a non-positive variance component is large precisely in those situations where a random-blocks analysis is useful – that is, when the block-to-block variation, relative to the total variation, is small. In contrast, the analysis in which the block effects are fixed is computationally simpler and less subjective. The loss in power for some BIBD with a fixed effects analysis is trivial. In such cases, we recommend treating the block effects as fixed. For response surface experiments designed in blocks, however, an opposite recommendation is made. When block effects are fixed, the variance of the estimated response surface is not uniquely estimated, and in practice this variance is obtained by ignoring the block effect. It is argued that a more reasonable approach is to treat the block effects to be random than to ignore it.     

A quick response production strategy to market demand

The reason for considering the quick response production strategy to market demand is due to the rapid technology change, which results in decreasing market price and obsolescence. This study considers a production strategy of locating final production line in response to the changes in market demand and the continuous deterioration in stock. The demand rate is assumed to decrease exponentially with time while the price is assumed to decrease linearly with time. The purpose of this study is to derive the most economical site of final-production line that assembles products with short life cycle. The model considered in this research takes into account the sales revenue, the deteriorating cost, the carrying cost, the variable cost and the fixed cost of production. Although there is a higher labour and material cost when the production site is located near market point, the total profit increases due to quicker responsive time, smaller import tax, lower inventory and lesser deteriorating cost.     

Accurate Response with Refurbished Consumer Returns

Centering around anticipative and reactive capabilities of firms, accurate response is an important supply‐side strategy to deal with demand uncertainty. Clearly, the structure of the possible reaction will crucially influence the optimal anticipative decision making. In this article, we extend the existing literature in this area by including a new reactive capability, namely the utilization of refurbished consumer returns from early sales to react to demand later in the selling season. Because consumer returns depend on previous sales, there is also a direct link to the anticipative supply decision. We capture this effect in a newsvendor‐type model and provide both analytical and numerical insights into the optimal anticipative and reactive decisions as well as the value of refurbishing in terms of the retailer's expected profitability.     

The relative impact of interviewer effects and sample design effects on survey precision

One of the principal sources of error in data collected from structured face-to-face interviews is the interviewer. The other major component of imprecision in survey estimates is sampling variance. It is rare, however, to find studies in which the complex sampling variance and the complex interviewer variance are both computed. This paper compares the relative impact of interviewer effects and sample design effects on survey precision by making use of an interpenetrated primary sampling unit–interviewer experiment which was designed by the authors for implementation in the second wave of the British Household Panel Study as part of its scientific programme. It also illustrates the use of a multilevel (hierarchical) approach in which the interviewer and sample design effects are estimated simultaneously while being incorporated in a substantive model of interest.     

Understanding the resilience of mail-back survey methods: An analysis of 20 years of change in response rates to national park surveys

Coverage and response rate challenges facing telephone and internet surveys have encouraged scientists to reconsider mail data collection methods. Although response rates to telephone surveys have declined sharply in the last 20 years, it is unclear how response rates to mail have fared during this time. This study analyzes 179 mail-back surveys of visitors to US National Parks from 1988 to 2007, which used virtually the same administration procedures throughout the period. Results show that response rates, based on only those who initially agreed to return a questionnaire, have remained at a high level with a 76% average while the number of questions and pages steadily increased. Despite this rise in response burden, rates have declined only moderately from about 80% in the late 1980s to about 70% more recently. The roles of additional contacts and survey salience in maintaining high response rates are examined. Results suggest that mail-back surveys for obtaining information from quasi-general public populations remain an effective data collection procedure.     

Bayesian estimation of quantile distributions

Use of Bayesian modelling and analysis has become commonplace in many disciplines (finance, genetics and image analysis, for example). Many complex data sets are collected which do not readily admit standard distributions, and often comprise skew and kurtotic data. Such data is well-modelled by the very flexibly-shaped distributions of the quantile distribution family, whose members are defined by the inverse of their cumulative distribution functions and rarely have analytical likelihood functions defined. Without explicit likelihood functions, Bayesian methodologies such as Gibbs sampling cannot be applied to parameter estimation for this valuable class of distributions without resorting to numerical inversion. Approximate Bayesian computation provides an alternative approach requiring only a sampling scheme for the distribution of interest, enabling easier use of quantile distributions under the Bayesian framework. Parameter estimates for simulated and experimental data are presented.     

Progressive multi-state models for informatively incomplete longitudinal data

Progressive multi-state models provide a convenient framework for characterizing chronic disease processes where the states represent the degree of damage resulting from the disease. Incomplete data often arise in studies of such processes, and standard methods of analysis can lead to biased parameter estimates when observation of data is response-dependent. This paper describes a joint analysis useful for fitting progressive multi-state models to data arising in longitudinal studies in such settings. Likelihood based methods are described and parameters are shown to be identifiable. An EM algorithm is described for parameter estimation, and variance estimation is carried out using the Louis’ method. Simulation studies demonstrate that the proposed method works well in practice under a variety of settings. An application to data from a smoking prevention study illustrates the utility of the method.