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

Results found: 8

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  Time series
help Sort By:

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

Non Linear Analysis of S&P Index

100%
Hanias M., Magafas L., Konstantaki P.
Equilibrium. Quarterly Journal of Economics and Economic Policy
|
2013
|
vol. 8
|
issue 4
125-135
EN
This paper applies non-linear methods to analyze and predict the daily open S&P index which is one of the most important stock index in the world. The aim of the analysis is to quantitatively show if the corresponding time series is a deterministic chaotic one and if one or more days ahead prediction can be achieved. These results make the present work a valuable tool for traders investors and funds.
2
Publication available in full text mode
Content available

Time-series dynamics of Baltic trade flows: Structural breaks, regime shifts, and exchange-rate volatility

100%
Hegerty S. W.
Journal of Economics and Management
|
2022
|
vol. 44
EN
Aim/purpose – In the decades since their reintegration with the West, the small open economies of Estonia, Latvia, and Lithuania have seen their trade flows grow substantially. While the mix of trade partners has evolved over time, the region has been affected by various political and economic shocks. This study examines the bilateral trade balances between the Baltic countries and nine partners to investigate whether there have been structural breaks due to political or economic events. Because these events may have been “priced into” exchange rates or increased these rates’ volatility, connections between these variables and trade balances are also considered. Design/methodology/approach – Monthly data beginning in 1994 are taken from the International Monetary Fund’s Direction of Trade Statistics [DOTS]. Trade partners include the Nordic countries of Finland, Sweden, and Norway, as well as Poland, Russia, and the United States and country groupings such as the CIS, Advanced Economies, and the World. Ratios of the export and import values are used to create bilateral trade balances. The Bai–Perron (1998) structural break test is then used to identify “break points” that can classify time periods into regimes. Baltic nominal and real effective exchange rates, both in log changes and as a GARCH-based volatility measure, show whether regimes correspond to competitiveness or risk. Correlations are calculated to show links between bilateral trade balances and real exchange rates. Findings – Each trade balance has at least one structural break; many have more. In fewer than half of the cases do these correspond to specific events such as EU accession or the Global Financial Crisis. Trade with Russia has decreased, particularly for Estonia and Latvia. But many partners with historical ties, such as Estonia-Finland, Latvia-Sweden, and Lithuania-Poland have more breaks than do other partners (such as Estonia-Poland). Structural breaks in real exchange-rate returns and volatility do not match those of trade balances, and correlations between returns and trade balances are low. Research implications/limitations – These findings open the door to future research on the macroeconomic and cultural/historical factors behind these trade linkages and any changes in regimes. However, no structural determinants have yet been estimated. Originality/value/contribution – This study isolates changes in trade regimes, which can be further explained by specific events or particular dates. It also shows that variance has changed as well as the mean, but this differs by country and by the partner.
3
Publication available in full text mode
Content available

Exchange market pressure, stock prices, and commodity prices east of the Euro

88%
Hegerty S. W.
Journal of Economics and Management
|
2018
|
vol. 31
74-94
EN
Aim/purpose – This paper aims to examine connections between the exchange, equity, commodity and commodity markets of a set of Central and Eastern European (CEE) economies using monthly time-series data. In particular, we examine whether stock – or commodity – price changes might put pressure on these currencies to depreciate, and whether these pressures are transmitted within the region or from larger neighbors. Design/methodology/approach – This paper creates monthly indices of Ex-change Market Pressure (EMP) from 1998 to 2017 using a combination of currency depreciation, reserve losses, and changes in interest-rate differentials for the Czech Republic, Hungary, Poland, and Ukraine, Bulgaria, and Romania. After examining these indices for evidence of currency ‘crises’, and their components for evidence of changes in currency policy, Vector Autoregressive (VAR) methods such as Granger causality and impulse-response functions are used to examine connections between EMP, domestic and foreign stock returns, and changes in commodity prices in the first four countries listed. Findings – While EMP increased in 2008, and the degree of central banks’ currency- -market interventions decreased afterward, this paper uncovers key differences among countries. In particular, the Czech Republic is relatively insulated from international transmissions, while Hungary is more susceptible to global spillovers and Poland is exposed to events originating elsewhere in the CEE region. Ukraine shows bidirectional causality between its EMP and stock indices, and finds that pressure on the hryvnia increases if commodity or oil prices decline. Research implications/limitations – This study adds to the relatively limited literature regarding this region, and highlights particular vulnerabilities for both individual countries and specific neighbors; further research is necessary to uncover the channels of transmission using economic modeling. Originality/value/contribution – This study explicitly models two major economic processes in a part of the world that is relatively rarely examined. These include events in Central and Eastern European exchange markets and central bank intervention, and also interlinkages among regional currency and equity markets, foreign equity markets, and global commodity prices. This will allow policymakers to assess integration between these countries, the rest of the European Union, and the global economy.
4
Publication available in full text mode
Content available

Obserwacje odstające na rynku energii elektrycznej

75%
Ganczarek-Gamrot A.
Studia Ekonomiczne
|
2016
|
vol. 288
7-20
PL
W pracy została przeprowadzona charakterystyka szeregów cen energii elektrycznej pod względem obserwacji, odstających na Polskiej Towarowej Giełdzie Energii (TGE). Do analizy zostały wykorzystane szeregi czasowe o dziennej częstotliwości indeksów IRDN, SIRDN, offIRDN, POLPXbase oraz POLPXpeak. Na podstawie wyników estymacji modelu ARIMA zostały zidentyfikowane obserwacje odstające: addytywne (AO), innowacyjne (IO), przesunięcie poziomu (LS) oraz tymczasowe zmiany (TC).
EN
In the paper outlier observations within time series of prices of electric energy from Polish Power Exchange were characterized. Time series of indexes IRDN, sIRDN, offIRDN, POLPXbase and POLPXpeak with daily frequency were analyzed. Additive outliers (AO), innovative outliers (IO), level shifts (LS), temporary change (TC) were identified using seasonal linear models SARIMA.
5
Publication available in full text mode
Content available

Identyfikacja obserwacji oddalonych w szeregach czasowych

75%
Trzęsiok M.
Studia Ekonomiczne
|
2016
|
vol. 265
95-105
PL
W artykule uwzględniono różne podejścia do zagadnienia identyfikacji obserwacji oddalonych: podejście dedykowane dla szeregów czasowych i modeli ARIMA, mierniki stopnia oddalenia obserwacji oraz metody klasyfikacyjne. Celem cząstkowym jest zestawienie istniejących metod, ze wskazaniem możliwości pewnych modyfikacji dla polepszenia wyników otrzymywanych z prowadzonej diagnostyki.
EN
The paper presents three different methods for detecting anomalies in time series. The first one is dedicated for time series analysis and ARIMA models. Two other two come from very different background: one is associated with measuring the distance from the given observation to the remaining objects in dataset. The other one belongs to the family of classification methods within machine learning framework. The goal of the paper is to present, compare and illustrate these three different approaches on a real world dataset.
6
Publication available in full text mode
Content available

Identyfikacja chaosu deterministycznego na podstawie liczby najbliższych sąsiadów

63%
Zeug-Żebro K.
Studia Ekonomiczne
|
2016
|
vol. 295
119-131
PL
Narzędzia służące do identyfikacji chaosu, pozwalają zwykle na wykrycie jedynie pojedynczego atrybutu dynamiki chaotycznej, np. wrażliwości na zmianę warunków początkowych, zatem przeprowadzenie bardziej wnikliwej analizy danych wymaga uwzględnienia uzupełniających się metod. Celem artykułu będzie identyfikacja chaosu deterministycznego na podstawie lokalnej aproksymacji wielomianowej, największego wykładnika Lapunowa oraz współczynnika DETM. W badaniach wykorzystane zostaną finansowe szeregi czasowe utworzone z cen zamknięcia wybranych indeksów giełd światowych.
EN
Methods of chaos identification typically allow detection of only a single attribute of the chaotic dynamics, such as e.g. a sensitivity to change of the initial conditions, therefore, to carry out a full analysis of the data requires consideration of the complementary methods. The aim of the article will be identification of chaotic dynamics in selected time series based on a local polynomial approximation, the largest Lyapunov exponent and the coefficient DETM. The test will be conducted based on the financial time series, which consist of closing prices of selected indices of stock exchanges worldwide.
7
Publication available in full text mode
Content available

Efektywność portfeli inwestycyjnych zbudowanych z wykorzystaniem największego wykładnika Lapunowa i wykładnika Hursta

63%
Miśkiewicz-Nawrocka M.
Studia Ekonomiczne
|
2018
|
vol. 366
118-134
XX
Badania nad zbudowaniem optymalnego portfela inwestycyjnego, zapoczątkowane w latach 50. ubiegłego wieku przez H. Markowitza, przyczyniły się do istotnego rozwoju dyscypliny naukowej, jaką jest analiza portfelowa. Prowadzone od tamtego czasu badania dostarczyły i wciąż dostarczają nowych narzędzi oraz podejść służących do wyznaczania udziałów instrumentów finansowych w portfelu, np. wskaźniki analizy fundamentalnej czy narzędzia do identyfikacji chaosu deterministycznego. Nowym podejściem zaproponowanym przez autora jest wykorzystanie w budowie portfela optymalnego zmodyfikowanej funkcji celu, zawierającej wariancję portfela i największy wykładnik Lapunowa lub wykładnik Hursta. Celem artykułu jest zbudowanie oraz ocena efektywności portfeli optymalnych wyznaczonych na podstawie zmodyfikowanej postaci funkcji celu.
EN
Initiated in the 1950s of the last century by H. Markowitz research on building the optimal portfolio investment contributed to the significant development of scientific discipline, which is the portfolio analysis. Studies conducted since then have provided and still provide new tools and approaches for determining the shares of financial instruments in the portfolio, eg. indicators of fundamental analysis, or tools for identifying deterministic chaos. The new approach proposed by the author is the use an modified objective function containing a portfolio variance and the largest exponent of Lapunov or the Hurst exponent in the construction of optimal portfolio. The purpose of the article is to build and evaluate the efficiency of optimal portfolios designated on the basis of a modified form of the objective function.
8
Publication available in full text mode
Content available

Badanie reakcji struktury rynku par walutowych G10 na sygnały makroekonomiczne z wykorzystaniem minimalnych drzew rozpinających na przykładzie ogłoszeń wskaźnika Nonfarm Payrolls

63%
Ozimek K.
Studia Ekonomiczne
|
2017
|
vol. 339
112-129
PL
Cząstkowym celem tego artykułu jest zbadanie stacjonarności procesów stochastycznych: jednokrokowego współczynnika przeżycia (SSSR) i logarytmicznej stopy zmian SSSR. Procesy te obrazują dynamikę minimalnego drzewa rozpinającego (MST) zastosowanego w badaniu do modelowania struktury sieci par walutowych G10. Celem głównym jest zbadanie reakcji jednego z wymienionych procesów zidentyfikowanego jako proces stacjonarny na ogłoszenia wskaźnika Nonfarm Payrolls (NFP) i tym samym sprawdzenie wpływu tego ogłoszenia na zmianę struktury wspomnianej sieci. Realizacja tego celu pozwoliła jednocześnie na weryfikację metody badawczej wykorzystującej MST. Do badania wybrano kwotowania 26 par walutowych w interwale 30-minutowym i zastosowano 111 momentów ogłoszeń wskaźnika NFP. Do konstrukcji minimalnego drzewa rozpinającego zastosowano symetryczną, jeśli chodzi o korelację, miarę odległości pomiędzy kwotowaniami par walutowych, co jest odmiennym podejściem w porównaniu z takim, w którym wykorzystuje się asymetryczną ze względu na korelację miarę odległości. Wykazano, że logarytmiczna stopa zmian SSSR jest procesem stacjonarnym oraz że ogłoszenie NFP wywołuje wyprzedzające to ogłoszenie zmiany w tym procesie i tym samym w strukturze sieci par walutowych G10.
EN
The partial purpose of this paper is to examine the stationarity of stochastic processes: the single-step survival ratio (SSSR) and logarithmic rate of change in the SSSR. These processes reflect the dynamics of a minimum spanning tree (MST) which is used in this research to model the structure of the network of G10 currency pairs. The main objective is to investigate the reaction to the announcement of the Nonfarm Payrolls indicator (NFP) of one of the above listed processes which has been identified as a stationary process and thereby verify the impact of this announcement on the change in the structure of the above mentioned network. Realization of this objective has allowed concurrently for verification of the research method utilizing MST. For this study, quotations of 26 currency pairs at 30-minute intervals have been selected and 111 moments when the NFP were released have been applied. For the construction of the minimum spanning tree, as to correlation, a symmetric distance measure between the quotes of currency pairs has been exploited which is different from such an approach, which uses, in terms of the correlation, an asymmetric distance measure. It has been shown that the logarithmic rate of change in the SSSR is a stationary process and that the release of the NFP triggers the leading changes in: this process, and thereby in the structure of the network of G10 currency pairs.
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.