Search

During the factory repairs of electric locomotives of all series and indices VL8, VL10, VL60, VL40, VL80, and VL82M (hereinafter referred to as VLv/i series electric locomotives) in the mid-20s, an unforeseen increase in the number of cast wheel centers with cracks was noted simultaneously at different domestic plants. The maximum number of axles of wheelsets withdrawn from service for various reasons was observed during 16–20 years of operation. At the same time, the duration of operation of a larger total number of wheel centers was more than 30 years. Cases of cracking in cast hub centers and spokes have been reported. There is a need for 100% control of hub cracks in the wheel centers of electric locomotives of the VLv/i series. The most common cause of failure of cast wheel centers in operation is their increased susceptibility to cracking due to casting defects. Increasing the service reliability of wheel centers is achieved by using rolled centers in locomotives, which have higher material quality and a homogeneous structure. Currently, no requirements are imposed on locomotive wheelsets in terms of the limiting value of the probability of cracking in wheel center hubs, which makes it impossible to predict their service life. So far, the peculiarities of fatigue cracks in the hubs of cast and rolled locomotive wheel centers operating under giga-cycle loading have not been sufficiently studied. An urgent task is to process statistical data on the establishment of wheelset mileages, particularly for the electric locomotives of the VLv/i series, with a given probability of the appearance of fatigue cracks. We assumed that the probability of safe mileage of wheel centers should be 0.001% with an acceptable probability of operation of the entire wheelset of 0.991. The given probability of safe operation of the wheelset centers of electric locomotives makes it possible to carry out a statistical analysis of the probability distribution of the mileage of the repaired wheel centers of each series of electric locomotives. The cumulative probability of failure-free operation of wheel centers is estimated using the central theorem, according to which the distribution function of the sum of a large number of independent random variables with a finite value of mathematical expectation and variance is reduced to the function of the normal probability distribution of the occurrence of unrepairable wheel centers of electric locomotives of this series. The analysis of the normal distribution of fatigue life under the giga-cycle loading of each series's wheel centers of electric locomotives allows one to determine the identity of their reliability. The problem of avoiding the unstable operation of locomotive repair plants without detecting out-of-service wheelset centers has been solved. [ABSTRACT FROM AUTHOR]

Bribery, as research issue, focuses on causality and impact analysis and in many cases has been subordinated as one of the many types of corruption. Using microdata from Transparency International's Global Corruption Barometer, the objective is to determine for a set of selected countries in Latin America and the Caribbean, the dependent variables to predict the probability of paying bribes when in contact with individuals, companies or entities that provide services. Inferential statistical techniques are used, such as logistic regression applying the maximum likelihood method and iterative process until the best model is found. From an initial survey with 117 variables, 11 variables were found to best explain the probability of paying a bribe. Variables such as level of schooling and the influence of officials and politicians affect people's willingness to pay a bribe. Significant topics of this study, such as retaliation to favor voting and sexual favors to receive benefits, although incipient in their study, are worth further research. This work can serve as a basis to motivate studies with microdata that help to better understand specific typologies of corruption through models that predict behaviors of ordinary citizens. [ABSTRACT FROM AUTHOR]

Separation of well section into permeable and impermeable parts is one of the main problems for further construction of a geological model, reserves estimation and field development planning. Quality of separation depends on amount of knowledge about geological section, level of theoretical development of well logging methods and general geophysical characteristics of the area. The fullest differentiation is obtained by using a complex of geological and geophysical methods. The paper is focused on Visean deposits of well of Sofyinskoe field drilled in 2014. A complex of activities was performed along with well logging. Porosity was calculated by acoustic and neutron logging. Core analysis was performed. Using well logging and results of core analysis selection was made, used for construction of statistical models. Based on statistical models all parameters were made-up to a single measurement system. The analysis of degree of influence of geological and geophysical parameters was made. The geological analysis shows that the greatest influence belongs to porosity and residual water. The geophysical analysis shows that the greatest influence belongs to hydrogen content and own radioactivity of rocks. A complex probabilistic parameter that includes all measurements according to core and geophysical parameters is calculated. Results of core analysis are considered fully in order to obtain a highest degree of difference. Almost all the parameters of geophysical data increase the degree of difference, except for lateral logging, microgradient and micropotential tools and transit time of P-wave for short tool, which reduces the degree of difference. Based on values of a complex parameter that have maximum differences in geological and geophysical parameters, relationships of geological and geophysical parameters were built. Scatter charts show that fields of measured points are not intersected, which confirms a correct separation of a section. Using a statistical method allows to consider fully available geological and geophysical data to separate a section into permeable and impermeable parts.

Many researchers want to unify probability and logic by defining logical probability or probabilistic logic reasonably. This paper tries to unify statistics and logic so that we can use both statistical probability and logical probability at the same time. For this purpose, this paper proposes the P–T probability framework, which is assembled with Shannon’s statistical probability framework for communication, Kolmogorov’s probability axioms for logical probability, and Zadeh’s membership functions used as truth functions. Two kinds of probabilities are connected by an extended Bayes’ theorem, with which we can convert a likelihood function and a truth function from one to another. Hence, we can train truth functions (in logic) by sampling distributions (in statistics). This probability framework was developed in the author’s long-term studies on semantic information, statistical learning, and color vision. This paper first proposes the P–T probability framework and explains different probabilities in it by its applications to semantic information theory. Then, this framework and the semantic information methods are applied to statistical learning, statistical mechanics, hypothesis evaluation (including falsification), confirmation, and Bayesian reasoning. Theoretical applications illustrate the reasonability and practicability of this framework. This framework is helpful for interpretable AI. To interpret neural networks, we need further study.

Body image perception comprises stable and dynamic representational features. Here, we examined whether a stable body image (BI) measure correlates to a dynamic sense of agency (SoA) score. Moreover, we tested whether differential BI perception scores predicts SoA performance under sensory conflict conditions. A total of 21 university students (age M=25.9, SD=9.29) completed the Brazilian version of the Silhouette Figures Scale (SFS) and participated in The Alien Hand Experiment (TAHE). TAHE is a task that manipulates participants' hand movement SoA. A Bayesian correlation matrix revealed substantial negative correlation probability between BI perception and SoA confidence in accuracy responses, specifically in experimental conditions where agency was manipulated. Based on the SFS scores, participants were divided into groups with and without evidences of BI distortion. Bayesian Independent Samples T-Tests evidenced substantial differential probability between groups. Analyzes confirmed lower SoA confidence among subjects with BI distortion greater than ±3 kg/m2. [ABSTRACT FROM AUTHOR]

Researchers typically use incentives (such as money or course credit) in order to obtain participants who engage in the specific behaviors of interest to the researcher. There is, however, little understanding or agreement on the effects of different types and levels of incentives used. Some results in the domain of statistical reasoning suggest that performance differences --- previously deemed theoretically important --- may actually be due to differences in incentive types across studies. 704 participants completed one of five variants of a statistical reasoning task, for which they received either course credit, flat fee payment, or performance-based payment incentives. Successful task completion was more frequent with performance-based incentives than with either of the other incentive types. Performance on moderately difficult tasks (compared to very easy and very hard tasks) was most sensitive to incentives. These results can help resolve existing debates about inconsistent findings, guide more accurate comparisons across studies, and be applied beyond research settings.

The objective of this paper was to establish disaggregation coefficients for the state of Minas Gerais, Brazil, under the premises of i) stationarity of the disaggregation coefficients according to the return period and ii) spatial validation of the disaggregation coefficients. The regression analysis was used as a statistical procedure to verify the significance of the coefficients of disaggregation slope coefficient as a function of return period in daily and sub-daily rainfall time series in rain gauges distributed throughout the state of Minas Gerais. Most of the disaggregation coefficients (94% of the situations) did not show a tendency to change due to the return period. The detected trends modified coefficients of disaggregation by up to 21% to the average obtained for different return periods. It was also verified that there is a significant difference between rainfall ratios of different durations, for different locations, indicating that the coefficients of disaggregation are not regional, but rather local. The use of disaggregation coefficients to obtain sub-daily rainfall is possible, provided that the representative coefficients of the locality are used. In this context, the spatialization of disaggregation coefficients is an important approach. • Relations between rainfall of different durations are disaggregation coefficients. • The use of disaggregation coefficients to obtain sub-daily rainfall is possible. • Disaggregation coefficients did not show a trend to change due to return period. • The disaggregation coefficients have local validity. • The spatialization technique can favor suitable disaggregation coefficients. [ABSTRACT FROM AUTHOR]

The history of Bayesian statistics is traced, from a personal perspective, through various strands and via its re-genesis during the 1960s to the current day. Emphasis is placed on broad-sense Bayesian methodology that can be used to meaningfully analyze observed datasets. Over 750 people in science, medicine, and socioeconomics, who have influenced the evolution of the Bayesian approach into the powerful paradigm that it is today, are highlighted. The frequentist/Bayesian controversy is addressed, together with the ways in which many Bayesians combine the two ideologies as a Bayes/non-Bayes compromise, e.g., when drawing inferences about unknown parameters or when investigating the choice of sampling model in relation to its real-life background. A number of fundamental issues are discussed and critically examined, and some elementary explanations for nontechnical readers and some personal reminiscences are included. Some of the Bayesian contributions of the 21st century are subjected to more detailed critique, so that readers may learn more about the quality and relevance of the ongoing research. A recent resolution of Lindley's paradox by Baskurt and Evans is reported. The axioms of subjective probability are reassessed, some state-of-the-art alternatives to Leonard Savage's axioms of utility are discussed, and Deborah Mayo and Michael Evan's refutation of Allan Birnbaum's 1962 justification of the likelihood principle in terms of the sufficiency and conditionality principles is addressed. WIREs Comput Stat 2014, 6:80-115. doi: 10.1002/wics.1293 For further resources related to this article, please visit the . Additional Supporting Information may be found at . Disclaimer: Reference to third party websites in this article does not constitute an endorsement or recommendation by the Publisher. Views and opinions expressed on third party websites are personal to the author and do not necessarily reflect those of this Publisher. Conflict of interest: The author has declared no conflicts of interest for this article. [ABSTRACT FROM AUTHOR]

In this article the author analyzes the values of two random variables (RV) - the body mass index (BMI) and the Pondera index (PI) of the competitors which ranked on the first six places on the contests without categories Mr Olympia, Arnold Classic, and Night of the Champions and Ironman during the 1980-2012 periods. The goal of the study was to establish the features of the probability density functions (PDF) of these indices and their changes with the time. After analyzing the data we reached to the following conclusions: 1. the body composition of the bodybuilders which ranked among the top six in the professional tournaments without categories is characterized by a clustering around the mean values in the studied indices - the sample is very homogeneous; 2. the form of the estimated PDF is intrusive for a bigger probability than the Normal distribution suggests for an emergence of competitors with extreme values of BMI and PI; 3. We consider that we could look for the reason for the increase of the values of both RVs with the time in two directions: 1. Because of the features of the judging and the ranking in the bodybuilding, the preferences of the judges evolved towards tolerating more muscular competitors or 2. The muscle mass of all the professional bodybuilders increased with the time in the studied time period which lead to an increase of the muscularity of the studied sample of bodybuilders. [ABSTRACT FROM AUTHOR]

The aim of the present study is to forecast thunderstorms over Kolkata (22°32′N, 88°20′E), India, during the pre-monsoon season (April-May) with graph spectral distance and entropy analysis. Graph vertices represent points connected by lines or edges, and lifting condensation level, convective condensation level, level of free convection, freezing level, level of neutral buoyancy and the surface level are taken as the input of the graph vertices. The variation in the most probable distance between the vertices is investigated. The result reveals a particular orientation of the vertex distances for thunderstorm days which is significantly different from the non-thunderstorm days. The reference graphs for thunderstorm and non-thunderstorm days are formed using the most probable vertex distances. The spectral distance between the reference graph and the graphs corresponding to thunderstorms are computed with the data collected during the period 1997-2009. The entropies, or the measure of disorderliness or uncertainty, are estimated for the graph distance matrices. The result shows that the thunderstorm days possess lower distance entropy than the non-thunderstorm days. This indicates that the reference graph that has been constructed for thunderstorms is more consistent. The result further depicts that the forecast accuracy through the present method is 98% with 1 h lead time, whereas the accuracy is 93% with 6 h lead time. The forecast is validated with the India Meteorological Department observations for the years 2007, 2008 and 2009. Copyright © 2011 Royal Meteorological Society [ABSTRACT FROM AUTHOR]

Abstract: An investigation was conducted in order to determine the viability of using two-point probability distribution functions to predict the material properties of two-phase heterogeneous materials. The material of interest in this investigation was Titanium Diboride/Alumina ceramic (TiB2 +Al2O3). In TiB2 +Al2O3 ceramics, it has been noted that the connectivity of the TiB2 second phase plays a major role in the mechanical properties of the TiB2 +Al2O3 ceramic, spall strength in particular. Two-point distribution functions were obtained for the four types of microstructures of TiB2 +Al2O3 and were compared to experimental results that have been previously reported. The two-point distribution functions showed very good correlation to connectivity and spall strength results. [Copyright &y& Elsevier]

A scheme is described for locally Bayesian parameter updating in models structured as successions of component functions. The essential idea is to back-propagate the target data to interior modules, such that an interior component's target is the input to the next component that maximizes the probability of the next component's target. Each layer then does locally Bayesian learning. The approach assumes online trial-by-trial learning. The resulting parameter updating is not globally Bayesian but can better capture human behavior. The approach is implemented for an associative learning model that first maps inputs to attentionally filtered inputs and then maps attentionally filtered inputs to outputs. The Bayesian updating allows the associative model to exhibit retrospective revaluation effects such as backward blocking and unovershadowing, which have been challenging for associative learning models. The back-propagation of target values to attention allows the model to show trial-order effects, including highlighting and differences in magnitude of forward and backward blocking, which have been challenging for Bayesian learning models. [ABSTRACT FROM AUTHOR]

The short tandem repeat allelic profiles at to 15 autosomal polymorphic loci were analyzed in four tribal populations of Mizoram (India). The analysis was performed on 354 unrelated healthy individuals belonging to Mongoloid races. All the samples were subjected to sex test (Amelogenin marker) besides the STR typing and in all instances; it has shown no deviation from expectation. The allele frequencies for all the analyzed loci in the studied populations are within expected range in comparison to the populations from same racial background. No significant deviation from the Hardy–Weinberg Equilibrium was observed for all the populations. In no cases the observed heterozygosity is less than that of expected values and it varied from 0.978 (Penta E) to as low as 0.425 (THO1). The discriminatory power and exclusion probability values for all the analyzed markers are significantly high and thus reveal high forensic significance. There is no evidence for association of alleles among the 15 studied loci. This allele frequency data will be useful for human identity testing in Mizo population. [Copyright &y& Elsevier]

The aim of the research was to create a model of steel fibre distribution in a Steel Fibre Reinforced Concrete space using statistical probability means. The model was created in order to better understand the behaviour of the composite under operating conditions. Four statistical distributions (Beta, Kumaraswamy, Three Parameter Beta and Generalised Transmuted Kumaraswamy) were examined to find the distribution that best described fibre settling phenomenon caused by manufacturing process conditions. In the next stage the chosen statistical distribution was adapted to create the model of steel fibre distribution in a Steel Fibre Reinforced Concrete space. The model took into account technological conditions such as vibrating time and properties such as consistency of the tested concrete. The model showed a good agreement with the real fibre distribution. [ABSTRACT FROM AUTHOR]

Petrophysical properties of tight sandstone reservoirs are complex which brings difficulties to fluid discrimination. Rock physics makes it possible to obtain petrophysical properties from elastic parameters. However, both deterministic rock physics and statistical rock physics have corresponding limitations. By combining deterministic rock physics and statistical rock physics, a joint posterior probability is proposed for fluid discrimination. To consider the effect of complex pore structure and permeability in tight sandstone reservoirs, a new deterministic rock physics model is built. In this model, soft porosity and connected porosity are quite important parameters to describe the above-mentioned reservoir characteristics. Assuming the noise follows a Gaussian distribution, we can obtain the posterior probability of gas saturation from the deterministic rock physics. Bayes discriminant is an effective method for statistical rock physics to estimate the prior, condition and posterior probabilities of petrophysical properties from well-logging data. Thus, the posterior probability of gas saturation belonging to the statistical rock physics is obtained. To guarantee the accuracy of fluid discrimination, the reflectivity method is used to achieve high-precision elastic parameters from seismic data. Application examples of well-logging data and seismic data confirm the validity of the proposed joint probabilistic fluid discrimination. • A new rock physics model for tight sandstones is built. • A joint probabilistic method is proposed for fluid discrimination. • The fluid prediction process of tight sandstone reservoirs is effective. • Reflectivity method is used to obtain high precision elastic parameters. [ABSTRACT FROM AUTHOR]

This study empirically re-examines fat tails in stock return distributions by applying statistical methods to an extensive dataset taken from the Korean stock market. The tails of the return distributions are shown to be much fatter in recent periods than in past periods and much fatter for small-capitalization stocks than for large-capitalization stocks. After controlling for the 1997 Korean foreign currency crisis and using the GARCH filter models to control for volatility clustering in the returns, the fat tails in the distribution of residuals are found to persist. We show that market crashes and volatility clustering may not sufficiently account for the existence of fat tails in return distributions. These findings are robust regardless of period or type of stock group. • The existence of fat-tails in stock return distribution is investigated. • Influential factors of stylized facts (e.g., market crash, volatility clustering) are considered. • These factors have a significant influence on the fat-tails in return distribution. • After controlling for these factors, evidence supporting the existence of fat-tails is still verified. • The fat-tails in return distributions cannot be sufficiently explained by the stylized facts. [ABSTRACT FROM AUTHOR]