Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 3

first rewind previous Page / 1 next fast forward last

Search results

help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

Metody prognozowania z wykorzystaniem trendu potęgowego

100%
Purczyński J.
Przegląd Statystyczny
|
2009
|
vol. 56
|
issue 2
52-66
EN
In this paper selected aspects concerning the use of power trend in the forecasting process were considered. Approximate methods for estimating trend parameters (equations (12)-(15)) were proposed. The methods yielded results similar to results given by least squares method (LSM). Formula (35) determining ex ante error of the forecast determined by the approximate methods and LSM for random element additive model was defined. Computer simulations were done – including three models of random element (additive, multiplicative, mixed) – with the aim of determining the range of usefulness of logarithmic transformation method, LSM and the approximate methods.
PL
W pracy rozpatrzono wybrane aspekty związane ze stosowaniem trendu potęgowego w procesie prognostycznym. Zaproponowano przybliżone metody estymacji parametrów trendu (wzory (12)-(15)), które prowadzą do zbliżonych wyników, jakie daje metoda najmniejszych kwadratów (MNK). Wyprowadzono wzór (35) określający błąd ex ante prognozy wyznaczonej metodami przybliżonymi oraz MNK dla addytywnego modelu składnika losowego. Wykonano symulacje komputerowe uwzględniające trzy modele składnika losowego (addytywny, multiplikatywny, mieszany) mające na celu określenie zakresu przydatności metody transformacji logarytmicznej, MNK oraz metod przybliżonych.
2

Simplified Method of GED Distribution Parameters Estimation

100%
Purczyński J.
Folia Oeconomica Stetinensia
|
2012
|
vol. 10
|
issue 2
35-49
EN
In this paper a simplified method of estimating GED distribution parameters has been proposed. The method uses first, second and 0.5-th order absolute moments. Unlike in maximum likelihood method, which involves solving a set of equations including special mathematical functions, the solution is given in the form of a simple relation. Application of three different approximations of Euler's gamma function value results in three different sets of results for which the χ2 test is conducted. As a final solution (estimation of distribution parameters) the set is chosen which yields the smallest value of the χ2 test statistic. The method proposed in this paper yields the χ2 test statistic value which does not exceed the value of statistic for a distribution with parameters obtained with the maximum likelihood method.
3

Estimation of the Shape Parameter of Ged Distribution for a Small Sample Size

63%
Purczyński J., Bednarz-Okrzyńska K.
Folia Oeconomica Stetinensia
|
2014
|
vol. 14
|
issue 1
35-46
EN
In this paper a new method of estimating the shape parameter of generalized error distribution (GED), called ‘approximated moment method’, was proposed. The following estimators were considered: the one obtained through the maximum likelihood method (MLM), approximated fast estimator (AFE), and approximated moment method (AMM). The quality of estimator was evaluated on the basis of the value of the relative mean square error. Computer simulations were conducted using random number generators for the following shape parameters: s = 0.5, s = 1.0 (Laplace distribution) s = 2.0 (Gaussian distribution) and s = 3.0.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.