Diffusive nested sampling

We introduce a general Monte Carlo method based on Nested Sampling (NS), for sampling complex probability distributions and estimating the normalising constant. The method uses one or more particles, which explore a mixture of nested probability distributions, each successive distribution occupying ∼e ⁻¹ times the enclosed prior mass of the previous distribution. While NS technically requires independent generation of particles, Markov Chain Monte Carlo (MCMC) exploration fits naturally into this technique. We illustrate the new method on a test problem and find that it can achieve four times the accuracy of classic MCMC-based Nested Sampling, for the same computational effort; equivalent to a factor of 16 speedup. An additional benefit is that more samples and a more accurate evidence value can be obtained simply by continuing the run for longer, as in standard MCMC.     

On limiting distribution laws of statistics analogous to pearson's chi-square

Two test-statistics analogous to Pearson's chi-square test function - given in (1.6) and (1.7) - are investigated. These statistics utilize, apart from the number of sample elements lying in the respective intervals of the partition, their positions within the intervals too. It is shown that the test-statistics are asymptotically distributed - as the sample size N tends to infinity - according to the x ²distribution with parameter r, i.e. the number of intervals chosen. The limiting distribution of the test statistics under the null-hypothesis when N tends to the infinity and r =O(N ^α) (0<α<1), further the consistency of the tests based on these statistics is considered. Some remarks are made concerning the efficiency of the corresponding goodness of fit tests also; the authors intend to return to a more detailed treatment of the efficiency later.     

Untersuchung der autoritären Einstellung bei ungarischen StudentInnen

We asked daytime university and college students to complete the survey, which aimed at examining the authoritarian attitude of those questioned, and the factors in connection to it. The questionnaire was made up of 23 statements, and those questioned had to express how far they agree on a five grade scale (N = 349). On the basis of the answers it could be stated that the different groups of those planning to work in different fields differ from each other also from the point of view of accepting authority: from those groups which were examined in greater numbers the physical education teachers and the theologians were the most authoritarian, while the social workers and students of human studies were the least. Those answering differed also in terms of religiousness: those considering themselves religious and close to the church seemed to be the most authoritarian and those who are not religious the least. The results were interestingly coloured by the fact that in assessing specific social situations the social workers and the convinced non-religious ones showed signs of more authoritarian attitude. Results also proved that the own opinion about authoritarianism is related to the opinion of the parents. Beside many other questions we also examined whether authoritarianism is related to the situation when someone is stricter to him/herself and to those emotionally closer than to others.     

Analyzing and clustering students' application preferences in higher education

We present a framework based on a higher education application preference list that allows a different type of flexible aggregation and, hence, the analysis and clustering of application data. Preference lists are converted into scores. The proposed approach is demonstrated in the context of higher education applications in Hungary over the period of 2006–2015. Our method reveals that efforts to leverage center-periphery differences do not fulfill expectations. Furthermore, the student''s top preference is very hard to influence, and recruiters may build their strategy on information about the first and second choices.     

Social Costs of Gambling in the Czech Republic 2012

Evidence about social costs of gambling is scarce and the methodology for their calculation has been a subject to strong criticism. We aimed to estimate social costs of gambling in the Czech Republic 2012. This retrospective, prevalence based cost of illness study builds on the revised methodology of Australian Productivity Commission. Social costs of gambling were estimated by combining epidemiological and economic data. Prevalence data on negative consequences of gambling were taken from existing national epidemiological studies. Economic data were taken from various national and international sources. Consequences of problem and pathological gambling only were taken into account. In 2012, the social costs of gambling in the Czech Republic were estimated to range between 541,619 and 619,608 thousands EUR. While personal and family costs accounted for 63% of all social costs, direct medical costs were estimated to range from 0.25 to 0.28% of all social costs only. This is the first study which estimates social costs of gambling in any of the Central and East European countries. It builds upon the solid evidence about prevalence of gambling related problems in the Czech Republic and satisfactorily reliable economic data. However, there is a number of limitations stemming from assumptions that were made, which suggest that the methodology for the calculation of the social costs of gambling needs further development.