Study of anaesthetical activity of alkoxyphenylcarbamic acid esters using statistical methods

Anaesthetical activity of 113 morpholinoethyl-, piperidinoethyl-, piperidinopropyl- and azepanoethyl- ester derivatives of alkoxyphenylcarbamic acid was characterized by several chemometrical techniques. The surface anaesthetical activity, A, and the infiltration anaesthetical activity, B, were correlated to lipophilicity, (expressed by the logarithm of the HPLC retention factor, log k), the length of the side alkoxy chain (represented by the number n of carbon atoms), molar mass M as well as the ester type. Principal component analysis and cluster analysis were used for predicting both types of the anaesthetic activity of the alkoxyphenylcarbamic acid esters.

Instead of laboratory: Analyzing data from natural experiments (Nobel Memorial Prize in Economic Sciences 2021)

The 2021 Nobel Prize in Economic Sciences was awarded to David Card, Joshua Angrist, and Guido Imbens for advancing methodology to establish casual relationships in economics. Their approach brought the notion of the natural experiment, situations in which heterogeneous reactions of different groups of people to chance shocks or policy changes allows to elicit causal effects, to the forefront of empirical analysis, and spearheaded a revolution in development of statistical methods needed to analyze the data. After the initial contributions in labor economics and economics of education, the new approach has become a new standard in economic sciences.

Developing New Software for Functional Food Production

Introduction. Statistical methods of data processing and IT technologies make it possible to introduce new modern methods of hazard and risk analysis in food industry. The research objective was to develop new software that would link together various risk-related production data. Study objects and methods. The research featured food production company LLC Yug (Biysk, Russia) that specializes in functional products and various ready-made software automation solutions. The study also involved statistical methods, methods of observation, collection of primary information, sequential top-down development of algorithms, and the Java programming language. Results and discussion. Food producers have a registration procedure for inconsistencies and violations of permissible limits at critical control points. The authors developed a new software program that allows production line operators to enter data on downtime and other violations of the production process. The program makes it possible for managers to receive up-to-date reports on various criteria, identify violations, and select appropriate corrective actions. This ready-made solution automates the process of accounting and hazard analysis. The program was tested at LLC Yug with the focus on the time that operators and managers needed to register the problem, analyze the data, develop corrective or preventive measures, and apply them. Conclusion. The new software proved to be less time-consuming than standard procedures applied in food industry and made it possible to save the time that operators and managers spent on decision making and reporting.

Effectiveness, Explainability and Reliability of Machine Meta-Learning Methods for Predicting Mortality in Patients with COVID-19: Results of the Brazilian COVID-19 Registry

The majority prognostic scores proposed for early assessment of coronavirus disease 19 (COVID-19) patients are bounded by methodological flaws. Our group recently developed a new risk score - ABC2SPH - using traditional statistical methods (least absolute shrinkage and selection operator logistic regression - LASSO). In this article, we provide a thorough comparative study between modern machine learning (ML) methods and state-of-the-art statistical methods, represented by ABC2SPH, in the task of predicting in-hospital mortality in COVID-19 patients using data upon hospital admission. We overcome methodological and technological issues found in previous similar studies, while exploring a large sample (5,032 patients). Additionally, we take advantage of a large and diverse set of methods and investigate the effectiveness of applying meta-learning, more specifically Stacking, in order to combine the methods' strengths and overcome their limitations. In our experiments, our Stacking solutions improved over previous state-of-the-art by more than 26% in predicting death, achieving 87.1% of AUROC and MacroF1 of 73.9%. We also investigated issues related to the interpretability and reliability of the predictions produced by the most effective ML methods. Finally, we discuss the adequacy of AUROC as an evaluation metric for highly imbalanced and skewed datasets commonly found in health-related problems.

Triangle Momentum

<p>This research investigates the breakout of security prices from periods of sideways drift known as Triangles. Contributions are made to the existing literature by considering returns conditionally based on Triangles in particular terms of how momentum traders time positions, and by then using alternative statistical methods to more clearly show results. Returns are constructed by scanning for Triangle events, and determining simulated trader returns from predetermined price levels. These are compared with a Naive model consisting of randomly sampled events of comparable measure. Modelling of momentum results is achieved using a marked point Poisson process based approach, used to compare arrival times and profit/losses. These results are confirmed using a set of 10 day return heuristics using bootstrapping to define confidence intervals. Using these methods applied to CRSP US equity data inclusive from years 1960 to 2017, US equities show a consistent but weak predictable return contribution after Triangle events occur; however, the effect has decreased over time, presumably as the market becomes more efficient. While these observed short term momentum changes in price have likely been compensated to a degree by risk, they do show that such patterns have contained forecastable information about US equities. This shows that prices have likely weakly been affected by past prices, but that currently the effect has reduced to the point that it is of negligible size as of 2017.</p>