A new approach to improving the type A uncertainty evaluation by cleaning of the collected data from unwanted influences which appears as non-periodical and periodical components identified in the data is presented in the paper. The approach refers to regularly in time sampled data. The non-periodical components are equivalent to trends while the periodical components are a type of disturbances of unknown a priori period. The cleaning process comply with the main stream of ISO GUM recommendation and can be recognized as good practice in uncertainty evaluation as the elimination of the influence like identified drift and periodic components are resulting in better approximation of the type A uncertainty. The proposed approach is discussed in the paper and the numerical result is presented as well.

After short introduction transfer coefficients of the unloaded four arms bridge of arbitrary variable arm resistances, supplied by current or voltage source, are given in Table 1. Their error propagation formulas are find and two rationalized forms of accuracy measures, i.e. related to the initial bridge sensitivities and of double component form as sum of zero error and increment error of the bridge transfer coefficients are introduced. Both forms of transfer coefficient measures of commonly used bridge - of similar initial arm resistances in balance and different variants of their jointed increments, are given in Table 3. As the example limited errors of some resistance bridges with platinum Pt100 industrial sensors of class A and B are calculated - Table 4 and analyzed. Presented approach is discussed and found as the universal solution for all bridges and also for any other circuits used for parametric sensors.

A brief review of some problems arising in the correct numerical expression and evaluation of results of indirect multi-parameter measurements is given. There is included a theoretical basis for determining the estimates of values, uncertainties and correlation coefficients of the indirectly obtained multi-measurand, which are processed from data of the simultaneously measured set of variables. The algebra of random vectors is used. A numerical example illustrates the linear transformation of two variables and the types of improperly evaluated results і that may occur with over-rounding. There are given thresholds of the safe uniform rounding of mean vector and its scatter ellipsoid. There is proposed an upgrading of the GUM Example H.2 and of the uncertainty equation for nonlinear functions. It is also evidenced that correlation matrix of 2010 data of fundamental physical constants recommended by CODATA has non-negligible negative eigenvalues. In the end of this work it is argued for the urgent needs of standardization of e-publication of the experimental data in two parts: e-printed traditional narrative part, and an attached computer readable file with all numerical input data and results, to allow "fast" numerical peer review of the proposed publication reporting new measurement results. This work is a result of an inter-disciplinary cooperation of a metrologist and a nuclear physicist.

Expanding of the application range of the GUM uncertainty type A evaluation method to the case of regularly sampled autocorrelated observations is described. As the first step is the previous identification and cleaning of the raw sample data from theregularly variable components. Then formulas for standard deviation of the mean value are expressed with the use of the so-called "effective number" of observations. This quantity depends on number of observations and on the sample autocorrelation function and allows calculating the expanded uncertainty due GUM recommendations. Given is method of estimation of autocorrelation function for the sample data.

Представлено расширение области ГУМ неопределенности типа А. Описан метод оценки для случая регулярных автокорреляционных наблюдений. В качестве первого шага использована первичная идентификация и очистка первичных данных выборки из различных переменных компонентов. Тогда формулы для стандартного отклонения от среднего значения выражаются с помощью так называемого "эффективного числа" наблюдений. Эта величина зависит от числа наблюдений, и автокорреляционная функция образца позволяет рассчитать расширенную неопределенность благодаря рекомендациям ГУМ. Приведён метод оценки автокорреляционной функции для выборки данных.

Наведено розширення області ГУМ невизначеності типу А. Описано метод оцінки на випадок регулярних автокореляційних спостережень. Як перший крок використано попередню ідентифікацію та очищення первинних даних вибірки з різних змінних компонентів. Тоді формули для стандартного відхилення від середнього значення виражаються за допомогою так званого "ефективного числа" спостережень. Ця величина залежить від числа спостережень, і автокореляційна функція зразка дозволяє розрахувати розширену невизначеність завдяки рекомендаціям ГУМ. Наведено метод оцінювання автокореляційної функції для вибірки даних.

In this paper some interesting and unexpected features of unconventionally supplied a four-terminal (4T) bridge network are presented. DC current source is switched in parallel to opposite arms supply this circuit which can contain the differential sensor (connected in neighbor arms). This circuit of two simultaneous outputs from the both bridge diagonals is named as double current (2J) bridge. The output voltages are different functions of arm resistance increments and their values are given in absolute and relative units. As the example of application circuit with two sensors acting simultaneously as strain gauge and as RTD's is proposed. Signal conditioning formulas of two-parameter measurement of strain and temperature are discussed in detail. Some results obtained with the use of this bridge circuit are briefly described. This new type DC bridge is dedicated as the input analogue conditioning circuit of all type resistance sensors used in measurement and diagnostic systems applied in industry and other fields including gas and petrol installations.

Знайдено статистики розподілів асиметрії та ексцесу та їх основних параметрів для вибірок певного малого числа елементів. Ці розподіли були визначені за допомогою методу Монте-Карло. Вибірки неодноразово витягували випадковим чином з нормально розподіленої генеральної сукупності. Знання про статистику асиметрії та ексцесу повинні дозволити одержати більш достовірні оцінки стандартного відхилення і невизначеності оцінюваного значення вимірюваної величини за вибірками з невеликим числом спостережень, коли діапазон їх розподілу відомий.