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

Results found: 6

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  exponential smoothing
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
EN
Quarterly employment rates in European countries are analysed in terms of the likelihood of achieving a specific employment rate within age and gender groups in a five-year horizon. The German employment rate serves as a benchmark for this research. The likelihood is estimated by a Monte-Carlo simulation based on the class of exponential smoothing models. The research presents a pessimistic prognosis of employment rates in European countries with respect to young and partly to older workers.
EN
In videogames industry, time series analysis can be very useful in determining the general evolution and behaviour of the market dynamics. These methods are applicable to any time series forecasting problem, regardless of the application sector. This article discusses time series approaches to forecast the sales of console games for the Italian market. In particular two univariate techniques were evaluated, exponential smoothing and the SARIMA technique. The aim is to exploit the capabilities of these statistical methods in order to have a comparison of the results and to choose the most accurate model through an ex-post evaluation. Using monthly time-series data from November 2005 to September 2017, the selection of the most suitable model was indicated by the smallest value of the measures of accuracy (MAPE, sMAPE, RMSE) for the out-of-sample observations regarding the period October 2017-September 2018. The implementation of the models was done using Forecast PRO and Gretl. The time series involved is related to the sales regarding the first party manufacturers of consoles and handhelds (Microsoft, Sony and Nintendo).
PL
Artykuł poświęcony jest wykorzystaniu wybranych modeli wyrównywania wykładniczego: Browna, Holta i Holta-Wintersa w prognozowaniu zmiennych ze złożona sezonowością w warunkach braku pełnej informacji. Prognozy wyjściowe będą budowane na podstawie szeregów oczyszczonych z sezonowości. Prognozy końcowe, uwzględniające wahania sezonowe, będą sumami prognoz wyjściowych i składników sezonowości lub iloczynami prognoz tego rodzaju i wskaźników sezonowości. Rozważania o charakterze teoretycznym zostaną zilustrowane przykładem empirycznym.
EN
The paper is devoted to the application of selected exponential smoothing models: Brown, Holt and Holt-Winters in prediction of variables with complex seasonality in the condition of lack of full information. Output forecasts will be built on the basis of time series cleansed from seasonality. Final forecasts, taking into account seasonal fluctuations, will be a sum of output forecasts and seasonal components or multiply of forecasts and the seasonal indicators. Theoretical considerations will be illustrated by an empirical example.
PL
W pracy przedstawione zostaną wyniki zastosowania modeli Browna, Holta i Holta-Wintersa w prognozowaniu zmiennej o bardzo wysokiej częstotliwości obserwowania w warunkach braku pełnej informacji na podstawie danych oczyszczonych z dwóch lub trzech rodzajów sezonowości. Rozpatrywany były dwa warianty luk systematycznych.
EN
In the paper will be presented results of the application of Brown, Holt and Holt-Winters models in the forecasting of a very high frequency variable in condition of lack of full information, based on seasonal adjusted time series, from which two or three types of seasonal fluctuations were removed. Two variants of systematic gaps were considered.
PL
W pracy przedstawione zostaną wyniki zastosowania wybranych modeli wyrównywania wykładniczego w prognozowaniu zmiennej o bardzo wysokiej częstotliwości, obserwowanej w okresach godzinnych, dla luk niesystematycznych, oczyszczonej z dwóch lub trzech rodzajów sezonowości. Rozpatrywany był wariant, w którym luki występują w każdym z rodzajów wahań składowych.
EN
In the paper will be presented the results of the application of selected models of exponential smoothing in forecasting of very high frequency variable, observed hourly, with unsystematic gaps, from which two or three types of seasonality fluctuation were eliminated. In the research was used a combination, in which gaps were present in each type of the fluctuation component.
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.