On classical and Bayesian order restricted inference for multiple exponential step stress model

In this article, we consider the multiple step stress model based on the cumulative exposure model assumption. Here, it is assumed that for a given stress level, the lifetime of the experimental units follows exponential distribution and the expected lifetime decreases as the stress level increases. We mainly focus on the order restricted inference of the unknown parameters of the lifetime distributions. First we consider the order restricted maximum likelihood estimators (MLEs) of the model parameters. It is well known that the order restricted MLEs cannot be obtained in explicit forms. We propose an algorithm that stops in finite number of steps and it provides the MLEs. We further consider the Bayes estimates and the associated credible intervals under the squared error loss function. Due to the absence of explicit form of the Bayes estimates, we propose to use the importance sampling technique to compute Bayes estimates. We provide an extensive simulation study in case of three stress levels mainly to see the performance of the proposed methods. Finally the analysis of one real data set has been provided for illustrative purposes.     

对《高海拔缺氧、文化和人类生育力或生殖能力》一文的评论

在戈尔斯坦、查隆和比尔最近发表的论文--<高海拔缺氧、文化和人类生育力或生殖能力的比较研究>(载<美国人类学家>85:28-49,1983)中,作者试图把文化当作解释喜马拉雅山区居民人口差异问题的惟一因素,完全排除了缺氧的影响,同时他们还对别人过去发表的用缺氧进行解释的相关材料(魏兹以及其他人1978;本格汉和塞奇勒1980;古朴塔1980)提出批评.     

Impact of Information Systems (IS) Steering Committees on IS Planning*

One of the most efficient ways to manage the information systems function is to introduce steering committees. It has been suggested that one of the foremost benefits of a steering committee is that it can improve the information systems planning efforts of an organization. However, there is very little empirical evidence in the literature that deals with how such committees affect planning. This study investigates the impact of steering committees on three phases of information systems planning: strategic planning, systems planning, and implementation of planning. The greatest impact of steering committees appears to be the strategic planning phase, while a lesser effect is observed in the systems planning and implementation of planning phases.     

Teacher Awareness and Attitudes Regarding Adolescent Risky Behaviours: Is Adolescent Gambling Perceived to be a Problem?

Despite legislative prohibitions, there is empirical evidence that youth gamble on both regulated and unregulated activities. The current survey was designed to assess teachers’ awareness and attitudes regarding adolescent gambling and other high-risk behaviours. Three-hundred and ninety teachers from Ontario and Quebec, with experience teaching students aged 12–18, completed an online survey. Results suggest that teachers are aware of the fact that youth gamble. Furthermore, they recognized the addictive nature of gambling and their subsequent consequences. Despite overestimating the proportion of youth experiencing gambling problems, gambling was viewed as being the least serious of issues affecting youth, with drug use and school violence topping the list. Almost half of respondents indicated that gambling in school can constitute a good learning activity. In regards to prevention, all other risky behaviours and academic problems were perceived as issues needing greater attention than gambling. These results, which are largely consistent with findings from a previous study examining parental perceptions of adolescent risky behaviours, suggest a need for greater awareness and teacher education.     

Is Economic Policy Uncertainty Related to Suicide Rates? Evidence from the United States

The main objective of this paper was to see whether different countries around the world show differences in their sustainability levels as captured in the indicators from the Sustainable Society Index (SSI, Van de Kerk and Manuel in Ecol Econ 66:228–242, 2012) according to their level of income. To do so, the X-STATIS and CO-STATIS multivariate techniques were employed. With these methods, our sample of 151 countries and 21 indicators can be jointly represented along four time periods. The results obtained permit us to visualize that the groups of countries by income levels show differences in some of the variables from the SSI, because of the lack of proximities between those variables and the countries. Moreover, with the X-STATIS technique, the possible evolution of the countries or indicators over time can be represented, and with CO-STATIS, the relations between the social, economic and environmental aspects can be shown as well. From our results we were able to deduce that, on the one hand, social and economic indicators, such as Public Debt or Employment, are associated with countries having high and upper-middle incomes, for example, Chile, Israel, Malta, Kuwait, Saudi Arabia, Oman, Spain, Portugal, France, Poland and Czech Republic. On the other hand, countries with low and lower-middle incomes are more associated with environmental issues. Also, after finding that the differences between the countries by income levels are mainly caused by the economic indicators, we carried out two CO-STATIS analyses, one for social and economic variables, and the other for economic and environmental variables. These findings led us to deduce that, generally, the social and economic indicators are not related to each other, nor are the economic indicators related to the environmental ones. However, for some of the countries individually both relations may be possible.     

A STOCHASTIC DOMINANCE ALGORITHM USING PIECEWISE LINEAR APPROXIMATIONS

Current stochastic dominance algorithms use step functions to approximate the cumulative distributions of the alternatives, even when the underlying random variables are known to be continuous. Since stochastic dominance tests require repeated integration of the cumulative distribution functions, a compounding of errors may result from this type of approximation. This article introduces a new stochastic dominance algorithm that approximates the cumulative distribution function by piecewise linear approximations. Comparisons between the new and old algorithms are performed for normally distributed alternatives. In about 95 percent of all cases, the two algorithms produce the same result.     

Family planning for the home,working wives and mothers

The Indian family planning program is discussed in relation to the home, working wives, and mothers. The major objectives of the program are to learn the reasons for the rapid growth of population, to discover suitable contraceptive techniques, advise, and reduce the birthrate to a level consonant with India's economic well being. Efforts to reach the home are made more difficult by geographic remoteness of some regions, sociological barriers, and the experience of infant mortality. Emphasis must be put on the fact that the fewer the children, the more hopeful the outlook for health and economic security. The trend today is for the middle classes to have fewer children than members of the lower classes. This situation should be reversed if India is to prosper. The hazzards to health of repeated childbirth are especially great to the working wife. Every large-scale industry should begin family planning clinics. By limiting family size, working wives can increase productivity and raise healthier and happier children; middle class wives will be able to respond to their desire to serve their country. Attitudes of working wives toward family planning is increasingly favorable. The most common deterrent to family planning use is fear of losing their children through death. Members of some communities also feel the need to increase the population of their community.     

Goodness-of-fit tests of hypothesized canonical variables

In the literature goodness-of-fit tests for canonical variables are available either in the x space or in the y space, see e.g., Bartlett (1951), Kshirsagar (1971, 1972), Radcliffe (1968), and Williams (1952). Here we present goodness-of-fit tests for canonical variables in both the x and y spaces. The results appear as extensions of the results of the above authors.     

On the estimation of restricted mean

In sampling from a continuous distribution with unknown mean μ and variance σ² the problem of estimation of μ, when it is known that μ∈(a, ∞) (or μ∈(-∞, b)), is considered. The estimators proposed here lie in the interval (a, ∞) (or (-∞, b)) almost surely. The performance of these estimators is compared to that of some known estimators in the case of sampling from a normal, exponential and a weighted difference of two independent chi-square distributions.