Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 16

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  sample size
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
Content available remote A tale of two stations: a note on rejecting the Gumbel distribution
EN
The existence of an upper limit for extremes of quantities in the earth sciences, e.g. for river discharge or wind speed, is sometimes suggested. Estimated parameters in extreme-value distributions can assist in interpreting the behaviour of the system. Using simulation, this study investigated how sample size influences the results of statistical tests and related interpretations. Commonly used estimation techniques (maximum likelihood and probability-weighted moments) were employed in a case study; the results were applied in judging time series of annual maximum river flow from two stations on the same river, but with different lengths of observation records. The results revealed that sample size is crucial for determining the existence of an upper bound.
EN
In the study the method of determination of the experiment size is provided so that the optimum reasoning could be applied on the basis of experiment results. The parameter estimation is examined here at the set absolute or relative error as well as hypothesis testing at pre-set (high) power. The considerations contained in the paper refer to success probability in binominal distribution. Such a distribution frequently occurs in the research in agricultural engineering.
3
Content available remote Portfolio Inputs Selection from Imprecise Training Data
EN
This paper explores very acute problem of portfolio secondary overfitting. We examined the financial portfolio inputs random selection optimization model and derived the equation to calculate the mean Sharpe ratio in dependence of the number of portfolio inputs, the sample size L used to estimate Sharpe ratios of each particular subset of inputs and the number of times the portfolio inputs were generated randomly. It was demonstrated that with the increase in portfolio complexity, and complexity of optimization procedure we can observe the over-fitting phenomena. Theoretically based conclusions were confirmed by experiments with artificial and real world 60,000-dimensional 12 years financial data.
EN
The availability of sample data, together with detailed environmental factors, has fueled a rapid increase in predictive modeling of species geographic distributions and environmental requirements. We founded that MaxEnt model has provided different descriptions of potential distributions based on different sample size, sample accuracy and environmental background. We used six combinations based on three sample data set and two kinds of environmental variables to estimate the potentially suitable areas of Brown Eared Pheasant (Crossoptilon mantchuricum) in MaxEnt model. The results show that the complex variables provided the higher AUC value and accurate potential distribution than simple variables based on the same size of samples. Complicated environmental factors combined with moderate size and accurate sample, can predict better results. The model results were scabrous based on simple environmental factors. Furthermore, big sample size and simple prediction environmental factors will reduce the prediction accuracy, whereas small samples provided a conservative description of ecological niche. Here, we highlighted that considering the big size and high accuracy of sample and many environmental factors of a species to minimize error when attempting to infer potential distributions from current data in MaxEnt model.
5
Content available remote Wpływ wielkości i kształtu próbki na wytrzymałość na ściskanie ABK
PL
W artykule przedstawiono wyniki badań wpływu kształtu i wymiarów próbki na wytrzymałość na ściskanie betonu komórkowego (ABK) klasy gęstości 600. Przeprowadzono klasyczne badania na całych elementach murowych oraz na wycinanych próbkach sześciennych i walcowych, wykazując istotny wpływ kształtu na wytrzymałość na ściskanie ABK. Obliczono znormalizowaną wytrzymałość na ściskanie pokazując, że współczynniki kształtu dają zawyżone wartości wytrzymałości na próbkach większych od próbek sześciennych.
EN
The article presents the results of the effect of the sample shape on the compressive strength of autoclaved aerated concrete (AAC) density class 600. Studies were carried out on whole masonry unit and cubic and cylindrical samples cut from whole units and has been shown that the shape of the sample has an influence on compressive strength of AAC. They were conducted normalized compressive mean strength of a masonry unit and show that the shape factors give inflated values of compressive strength.
6
Content available remote Wpływ kilku czynników na wyniki normowego oznaczania nasiąkliwości betonu
PL
Przeprowadzono badania czynników wpływających na wyniki oznaczeń nasiąkliwości betonu. Uzyskane wyniki wykazały, że nasycanie wodą kostek betonowych o wymiarach 10 cm i 15 cm można zakończyć po 4 dniach. Nie stwierdzono wpływu trzech rodzajów cementów: CEM I 42,5, CEM II/B-V 32,5, CEM III/ A HSR/LH/NA. Brak wpływu stosunku w/c w zakresie 0,38, 0,44 i 0,50. Decydujący wpływ na wyniki ma czas suszenia próbek: w przypadku kostek 10 cm wynosi on 5 do 8 dni a 15 cm 6 do 11 dni, w zależności od przyjętej zmiany masy. W przypadku CEM III powinien on być dłuższy o 1 do 2 dni. Jest mniejsza nasiąkliwość kostek 15 cm od kostek 10 cm. Nasiąkliwość w przypadku zmiany masy <0,2% jest mniejsza niż <0,1%.
EN
The selected factors influence on water absorption of concrete was tested. The experimental results have shown that the water saturation of concrete cubes of 10 cm and 15 cm dimensions can be ended after 4 days. No influence of three types of cement: CEM I 42.5, CEM II/B-V 32.5, CEM III/A HSR/LH/NA. Also w/c ratio in the range 0.38, 0.44 and 0.50 has no effect. The decisive influence on the absorption results has the drying time: in the case of cubes of 10 cm it should be in the range of 5 to 8 days and 15 cm cubes between 6 and 11 days, depending on adopted mass change. In the case of CEM III it should be longer from 1 to two days. The absorption is lower in the case of 15 cm cubes, comparing to 10 cm cubes. Absorption for mass change <0.2% is lower than in the case of <0.1%.
PL
Przeprowadzono badania przyczepności elementów zespolonych złożonych z dwóch betonów o różnym czasie dojrzewania, ocenianej metodą rozłupywania. Stwierdzono, że wytrzymałość przyczepności zależy od wielkości elementów zespolonych, a więc podlega efektowi skali. Natomiast nie stwierdzono różnic przyczepności w przypadku gdy elementy te były wykonano z dwóch betonów tej samej klasy, lub różnych klas.
EN
The adhesion of two concrete placed at different time, being the members of composite element, was tested applying splitting method. It was establish that the adhesion strength is different for the variable dimensions of these composite elements, thus is depending of the size effect. However, no differences of adhesion strength were found when comparing two elements, which members were produced of concretes having the same or different strength.
8
Content available remote A Note on a priori Estimations of Classification Circuit Complexity
EN
The paper aims at tight upper bounds on the size of pattern classification circuits that can be used for a priori parameter settings in a machine learning context. The upper bounds relate the circuit size S(C) to n_L := .log_2mL., where mL is the number of training samples. In particular, we show that there exist unbounded fan-in threshold circuits with less than (a) [formula] gates for unbounded depth, (b) SL [formula] gates for small bounded depth, where in both cases all mL samples are classified correctly. We note that the upper bounds do not depend on the length n of input (sample) vectors. Since n_L << n in real-world problem settings, the upper bounds return values that are suitable for practical applications. We provide experimental evidence that the circuit size estimations work well on a number of pattern classification tasks. As a result, we formulate the conjecture that [formula] gates are sufficient to achieve a high generalization rate of bounded-depth classification circuits.
PL
W artykule przedstawiono analizę metod wyznaczania liczebności próbki jednostek wyrobów wymaganych do statystycznej oceny procesu obróbki. Omówiono metody ustalania liczebności próbki oparte na pojęciu zmiennej standaryzowanej, na wartości krytycznej statystyki t- Studenta i na analizie graficznej wartości krytycznych statystyki t. Dodatkowo przeprowadzono praktyczną weryfikację analizowanych metod uwzględniając w badaniach ocenę wartości średniej i oszacowanie odchylenia standardowego odchyłek geometrycznych. Wyniki analiz i badań przedstawiono w postaci graficznej i tabelarycznej.
EN
The article presents an analysis of the methods of determining the size of a sample of product units required for the statistical evaluation of the process of machining. Discussed are sample size determination methods based on the concept of standardized variable, the critical value of Student's t-statistic, and the graphic analysis of critical values of the t statistic. Additionally, a practical verifi cation of the analyzed methods was conducted, taking into account the estimate of the mean value and the estimation of the standard value of geometric deviations. The results of the analyses are presented graphically and in tabular form.
PL
W pracy zastosowano metodę wyznaczania odpowiedniej liczebności próby w celu podzielenia badanych populacji na trzy rozłączne grupy, jednorodne pod względem średniej wartości modułu sprężystości miąższu jabłek. Pozwoliło to na wskazanie sposobów przechowywania owoców wybranych odmian jabłoni, które powodują obniżenie lub podwyższenie ich modułu sprężystości.
EN
In the work, in order to divide the tested populations into three disjoint groups, homogeneous in terms of average value of modulus of elasticity of apple flesh, a method of setting out appropriate sample size was applied. This allowed to indicate ways of storing fruits of selected apple varieties, which lowers or increases their modulus of elasticity.
11
Content available Wybrane sposoby określania liczności próby
PL
W analizie statystycznej wydarzeń w siłowni okrętowej, i nie tylko, istnieje konieczność określania liczności próby. Nie jest ona wymagana, jeżeli zebrane wyniki nie są obrabiane aparatem statystycznym, a służą tylko do zaprezentowania zaobserwowanych zjawisk lub przebiegów. W prezentowanym materiale przedstawiono niektóre sposoby określania liczności próby oraz pobierania próby. Scharakteryzowano losowanie próby ze zbioru nieznanego i z tzw. warstw, wielostopniowe i systematyczne oraz wiązkami. Przedstawiono również uwagi o kosztach pobierania próby i proporcjach w próbie.
EN
There is a need for specifying a sample size in statistical analysis of, among others, marine power plant events. Sample size is not required when the collected results are not processed with statistical tools, but only are used to present observed phenomena. This work points out some of the methods of sample size determination and drawing a sample. The authors describe the drawing of a sample from an unknown set, from layers, multistage, systematic and in bundles. Remarks on costs of sampling and on proportions in a sample are also given.
PL
W pracy zastosowano procedurę porządkowania średnich w celu wyłonienia „najlepszych”, pod względem uzyskiwanych wartości modułu sprężystości miąższu jabłek, kombinacji odmiany i czasu składowania. Obliczono prawdopodobieństwa wyboru „najlepszych” kombinacji dla pewnej ustalonej liczebności próbek, a także wyznaczono właściwe liczebności próbek dla z góry zadanych wartości prawdopodobieństw.
EN
Procedure of ordering mean values to point out the “best” ones, considering obtained values of apple flesh elasticity modulus, as well as the variety and storage tome combination, was applied in the study. Probability of choosing “best” combination for assumed number of samples was also determined for assumed probability values.
13
Content available remote Models of relative abundance distributions. 1, Model fitting by stochastic models
EN
The present paper studies possibilities to discriminate between 9 stochastic models of relative abundance distributions (RADs). It develops a new test statistic for fitting based on least square distances and tests the applicability of methods described so far. The paper identifies three basic shapes of RADs termed power fraction, random assortment and Zipf-Mandelbrot type shape. It is shown that even a correct identification of the shape of a given data set requires that this data set is replicated more than 10 times. Estimates of necessary sample sizes for real animal or plant communities revealed that for communities with 20 to 100 species at least 200 to 500 times the species number is necessary for a correct model identification. The implications of these findings for the applicability of models of relative abundance distributions are discussed
14
Content available remote Impact of statistical methodology on phase II clinical trials in oncology
EN
The present paper was motivated by the experience matured by the Author as member of numerous Ethical Committee in some twenty years. After realizing that the protocols of phase II trials appeared questionable from a methodological wiepoint the Author, together with his colleague L. Mariani of the National Institute of Tumours in Milan decided to develop a two step research. In the first one the statistical features of phase II design based on frequentist, Baysian and decision theory approaches were thoroughly investigated. In the second step the practical application of these design in planning and conducting phase II trials in oncology was studied. The present paper gives a synopsis of the results emerging from the whole research.
PL
Przedstawiona praca zawiera analizę dwuetapowych badań klinicznych. Podczas pierwszego etapu ustalany jest plan przyszłych badań. Wykorzystuje się tu elementy teorii decyzji oraz wnioskowanie częstotliwościowe. Drugi etap obejmuje zastosowania utworzonych podczas pierwszego etapu schematów w rozwiązywaniu wybranych problemów onkologicznych badań klinicznych.
EN
The aim of this paper is to stress the importance of a proper statistical determination of the sample size in experimental research, and to underline the possible effect of an experiment with an inadequate number of cases on the results. The first part of the paper introduces the statistical concepts needed for the sample size calculation. Type I and II errors are defined and the associated probabilities are presented. Statistical power of a test is explained and its correlation with the sample size and experimental variability is defined. In a second section, the criteria for the calculation of the sample size are described. In the third part of the article, a statistical comparison between a real experiment and a numerical simulation is shown to highlight the consequences of the selection of different sample sizes. The risk of drawing mistaken conclusions caused by an inadequate sample size calculation is thus calculated.
16
EN
On the basis of large model assemblages estimators are developed to predict the sample size necessary to sample a given fraction of the total species number. The classical method that takes the point of leveling off of the species accumulation curves proved to be less efficient than the use of the second order jackknife in determining the sample size necessary to collect exactly half of the species number (N[O.5]). The present paper studies eight newly developed estimators for N[O.5] and shows that estimators based on a Michaelis-Menten formula and a negative exponential model give even better results with minimal sampling effort. The quality of all estimators was not correlated with simple measures of community structure.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.