Concepts Of Statistical Analysis Research Articles

Foundations of probability-raising causality in Markov decision processes

This work introduces a novel cause-effect relation in Markov decision processes using the probability-raising principle. Initially, sets of states as causes and effects are considered, which is subsequently extended to regular path properties as effects and then as causes. The paper lays the mathematical foundations and analyzes the algorithmic properties of these cause-effect relations. This includes algorithms for checking cause conditions given an effect and deciding the existence of probability-raising causes. As the definition allows for sub-optimal coverage properties, quality measures for causes inspired by concepts of statistical analysis are studied. These include recall, coverage ratio and f-score. The computational complexity for finding optimal causes with respect to these measures is analyzed.

A study of repeatability of hot smoke test in a subway station

Hot smoke test is a key method for fire studies in metro systems. But most hot smoke test scenarios are conducted only once, which ignores the experiment uncertainties and errors. To quantify the uncertainty and repeatability of hot smoke tests in subway stations, seven experiments are repeated on a station platform. 120 thermistors are deployed among the platform to acquire the temperature curves in the experimental area. The concept of statistical analysis and functional analysis is adopted to study the error and turbulence caused by random effects. The results indicate that: (1) According to the fluctuation properties, the experiment area is divided into fire plume area and ceiling jet area. The data uncertainty of the fire plume area is significantly higher than the ceiling jet area. (2) The repeatability of temperature data in the fire plume area is poor. The difference between single experiment curve and average curve might reach 23%–24%. (3) The repeatability of the data in the ceiling jet area is much better with a deviation smaller than 7.8%. The validated experiment data presented in this work could be used for simulation model verification. The repeatability analysis method presented is applicable for other fire studies.

The Multi-Objective Optimization of Headlamp Lighting System

When designing headlights using optical software LightTools, we found that the maximum illuminance and facula diameter of the initial headlamp lighting system design were less than 20000 lux (maximum illuminance) and 40mm (facula diameter), which did not meet the minimum performance requirements. However, if we increase the maximum illuminance value, the facula diameter value will become smaller and may not meet the minimum performance requirements. In order to obtain the best value of maximum illuminance and facula diameter at the same time, we used a multi-objective optimization method (combination of Taguchi method and robust multiple criterion optimization approach (RMCO)) to solve maximum illuminance and facula diameter optimization problem. It is effective and helpful increase the maximum illuminance and facula diameter of the headlamp lighting system (The maximum illuminance increased from 9580 lux to 22900 lux, the facula diameter increased from 40mm to 50mm). In this method, the concept of statistical analysis is used to obtain a set of diversified Pareto-optimal solutions. The set of diversified Pareto-optimal solutions can obtain for energy optimized design of headlamp lighting system. This study is the first attempt to use the RMCO method to optimize the multi-objective problem in a headlamp lighting system.

Application of multivariate statistical analysis concepts for assessment of hydrogeochemistry of groundwater\u2014a study in Suri I and II blocks of Birbhum District, West Bengal, India

Multivariate statistical techniques, cluster and principal component analysis were applied to the data on groundwater quality of Suri I and II Blocks of Birbhum District, West Bengal, India, to extract principal factors corresponding to the different sources of variation in the hydrochemistry as well as the main controls on the hydrochemistry. For this, bore well water samples have been collected in two phases, during Post-monsoon (November 2012) and Pre-monsoon (April 2013) from 26 sampling locations spread homogeneously over the two blocks. Excess fluoride in groundwater has been reported at two locations both in post- and in pre-monsoon sessions, with a rise observed in pre-monsoon. Localized presence of excess iron has also been observed during both sessions. The water is found to be mildly alkaline in post-monsoon but slightly acidic at some locations during pre-monsoon. Correlation and cluster analysis studies demonstrate that fluoride shares a moderately positive correlation with pH in post-monsoon and a very strong one with carbonate in pre-monsoon indicating dominance of rock water interaction and ion exchange activity in the study area. Certain locations in the study area have been reported with less than 0.6 mg/l fluoride in groundwater, leading to possibility of occurrence of severe dental caries especially in children. Low values of sulfate and phosphate in water indicate a meager chance of contamination of groundwater due to anthropogenic factors.

Network anomaly diagnosis via statistical analysis and evidential reasoning

This paper investigates the efficiency of diagnosing network anomalies using concepts of statistical analysis and evidential reasoning. A bi-cycle of auto-regression is first applied to model increments in the values of network monitoring variables to accurately detect network anomalies. To classify the rootcause of the detected anomalies, concepts of evidential reasoning of Dempster-Shafer theory are employed; the root-cause of a network failure is inferred by gathering pieces of evidence concerning different groups of candidate failures obtained from a training set of detected anomalies and their corresponding root-causes. These groups are then refined to infer the exact cause of failure when evidence accumulates using the Dempster rule of combinations. To handle cases of imbalanced training sets, two new approaches for assigning belief values to different anomaly classes are also proposed. Performance analysis and results demonstrate the accuracy of the proposed scheme in detecting anomalies using real data.

Introduction to biostatistics: Part 1, basic concepts

Statistical methods commonly used to analyze data presented in journal articles should be understood by both medical scientists and practicing clinicians. Inappropriate data analysis methods have been reported in 42% to 78% of original publications in critical reviews of selected medical journals. The only way to halt researchers' misuse of statistics and improve the clinician's knowledge of statistics is through education. This is the first of a six-part series of articles intended to provide the reader with a basic, yet fundamental knowledge of common biomedical statistical methods. The series will cover basic concepts of statistical analysis, descriptive statistics, statistical inference theory, comparison of means, chi 2, and correlational and regression techniques. A conceptual explanation will accompany discussion of the appropriate use of these techniques.