Wyniki wyszukiwania - Biblioteka Nauki

1

Price duration versus trading volume in high-frequency data for selected DAX companies

100%

Gurgul H. , Syrek R. , Mitterer C.

Managerial Economics

|

2016

|

tom Vol. 17, no. 2

241--260

EN

The main goal of this paper is to gain insights into the dependence structure between the duration and trading volume of selected stocks listed on the Frankfurt Stock Exchange. We demonstrate the usefulness of the copula function to describe the dependence of specific unevenly spaced time series. The properties of the time series of price durations and trading volumes under study are in line with common observations from other empirical studies. We observe clustering, overdispersion, and diurnality. For most of the stocks, the seminal model (linear parametrization with exponential or Weibull distribution) can be replaced by a logarithmic specification with more-flexible conditional distributions. The price duration and trading volume associated with this duration exhibit dependence in the tails of distribution. We may conclude that high cumulative trading volumes are associated with long duration. However, changes of price over short times are related to low cumulative volume.

2

New copulas based on general partitions-of-unity and their applications to risk management (part II)

100%

Pfeifer D. , Mändle A. , Ragulina O.

|

2017

|

tom 5

|

nr 1

246-255

EN

We present a constructive and self-contained approach to data driven infinite partition-of-unity copulas that were recently introduced in the literature. In particular, we consider negative binomial and Poisson copulas and present a solution to the problem of fitting such copulas to highly asymmetric data in arbitrary dimensions.

3

New copulas based on general partitions-of-unity and their applications to risk management

100%

Pfeifer D. , Tsatedem H. A. , Mändle A. , Girschig C.

|

2016

|

tom 4

|

nr 1

EN

We construct new multivariate copulas on the basis of a generalized infinite partition-of-unity approach. This approach allows, in contrast to finite partition-of-unity copulas, for tail-dependence as well as for asymmetry. A possibility of fitting such copulas to real data from quantitative risk management is also pointed out.

4

Copula–Induced Measures of Concordance

100%

Fuchs S.

|

2016

|

tom 4

|

nr 1

EN

We study measures of concordance for multivariate copulas and copulas that induce measures of concordance. To this end, for a copula A, we consider the maps C → R given by [...] where C denotes the collection of all d–dimensional copulas, M is the Fréchet–Hoeffding upper bound, Π is the product copula, [. , .] : C × C → R is the biconvex form given by [C, D] := ∫ [0,1]d C(u) dQD(u) with the probability measure QD associated with the copula D, and ψΛ C → C is a transformation of copulas. We present conditions on ψΛ and on A under which these maps are measures of concordance. The resulting class of measures of concordance is rich and includes the well–known examples Spearman’s rho and Gini’s gamma.

5

Joint weak hazard rate order under non-symmetric copulas

100%

Pellerey F. , Spizzichino F.

|

2016

|

tom 4

|

nr 1

EN

A weak version of the joint hazard rate order, useful to stochastically compare not independent random variables, has been recently defined and studied in [4]. In the present paper, further results on this order are proved and discussed. In particular, some statements dealing with the relationships between the jointweak hazard rate order and other stochastic orders are generalized to the case of non symmetric copulas, and its relations with some multivariate aging notions (studied in [2]) are presented. For this purpose, the new notions of Generalized Supermigrative and Generalized Submigrative copulas are defined. Other new results, examples and discussions are provided as well.

6

Baire category results for quasi–copulas

100%

Durante F. , Fernández-Sánchez J. , Trutschnig W.

|

2016

|

tom 4

|

nr 1

EN

The aim of this manuscript is to determine the relative size of several functions (copulas, quasi– copulas) that are commonly used in stochastic modeling. It is shown that the class of all quasi–copulas that are (locally) associated to a doubly stochastic signed measure is a set of first category in the class of all quasi– copulas. Moreover, it is proved that copulas are nowhere dense in the class of quasi-copulas. The results are obtained via a checkerboard approximation of quasi–copulas.

7

An empirical almost sure central limit theorem under the weak dependence assumptions and its application to copula processes

100%

Dudziński M.

Annales Universitatis Mariae Curie-Skłodowska, sectio A – Mathematica

|

2017

|

tom 71

|

nr 1

EN

Let: \(\mathbf{Y=}\left( \mathbf{Y}_{i}\right)\), where \(\mathbf{Y}_{i}=\left( Y_{i,1},...,Y_{i,d}\right)\), \(i=1,2,\dots \), be a \(d\)-dimensional, identically distributed, stationary, centered process with uniform marginals and a joint cdf \(F\), and \(F_{n}\left( \mathbf{x}\right) :=\frac{1}{n}\sum_{i=1}^{n}\mathbb{I}\left(Y_{i,1}\leq x_{1},\dots ,Y_{i,d}\leq x_{d}\right)\) denote the corresponding empirical cdf. In our work, we prove the almost sure central limit theorem for an empirical process \(B_{n}=\sqrt{n}\left( F_{n}-F\right)\) under some weak dependence conditions due to Doukhan and Louhichi. Some application of the established result to copula processes is also presented.

8

Miltivariate measures of dependence based on copulas

100%

Heilpern S.

Mathematical Economics

|

2014

|

nr 10(17)

17-32

EN

The paper is devoted to the multivariate measures of dependence. In contrast to the classical approach, where the pairs of variables are studied, we investigate the dependence of more than two variables. We mainly consider the measures based on copulas. These are the multivariable generalizations of the known coefficients of such correlation as Spearman’s rho, Kendall’s tau, Blomquist’s beta and Gini’s gamma. We present the definitions, the constructions and the basic properties of such multivariate measures of dependence. The case of large number of dimension, greater than two, presents more complications. We have several different versions of such generalization in this case and the lower bound of the values of such measures of dependence are close to zero. We also study the multivariate tail dependences. The last part of the paper is devoted to the estimation of multivariable versions of Spearman’s rho coefficient.

9

Price duration versus trading volume in high-frequency data for selected DAX companies

100%

Gurgul H. , Robert S. , Mitterer C.

|

tom 17

|

nr 2

241-260

EN

The main goal of this paper is to gain insights into the dependence structure between the duration and trading volume of selected stocks listed on the Frankfurt Stock Exchange. We demonstrate the usefulness of the copula function to describe the dependence of specific unevenly spaced time series. The properties of the time series of price durations and trading volumes under study are in line with common observations from other empirical studies. We observe clustering, overdispersion, and diurnality. For most of the stocks, the seminal model (linear parametrization with exponential or Weibull distribution) can be replaced by a logarithmic specification with more-flexible conditional distributions. The price duration and trading volume associated with this duration exhibit dependence in the tails of distribution. We may conclude that high cumulative trading volumes are associated with long duration. However, changes of price over short times are related to low cumulative volume.

10

The structure of contemporaneous price-volume relationships in financial markets.

88%

Gurgul H. , Syrek R.

Managerial Economics

|

2013

|

tom 14

39-60

EN

The main goal of this paper is an examination of the interdependence stuctures of stock returns, volatility and trading volumes of companies listed on the CAC40 and FTSE100. The authors establish that the mean values of respective measures are different on the markets under study. In general, they are larger for equities from CAC40 than from FTSE100. The Mixture of Distributions Hypothesis with long memory is rejected for about 70 % of stocks from both markets. Additionally fractional cointegration was tested. The lack of fractional cointegration, suggests a rejection of the last variant of MDH in all cases, i.e. the time series under study do not exhibit common long-run dependence. The analyzed time series are not driven by a common information arrival process with long memory. Correlation between volatility and trading volume is present for all the stocks of companies from these markets. The mixtures of rotated copulas and Kendall correlation coefficient allowed the checking of extreme return-volume dependence structures. The empirical results reflect significant dependencies between high volatility and high trading volume. In general, the dependence structures of stock returns and trading volume are different. In the case of CAC40 companies high trading volume is not correlated as frequently with high stock returns as with low stock returns. For companies listed on the FTSE100 high stock returns are mostly related with high trading volume.

11

A Biconvex Form for Copulas

88%

Fuchs S.

|

2016

|

tom 4

|

nr 1

EN

We study the integration of a copula with respect to the probability measure generated by another copula. To this end, we consider the map [. , .] : C × C → R given by [...] where C denotes the collection of all d–dimensional copulas and QD denotes the probability measures associated with the copula D. Specifically, this is of interest since several measures of concordance such as Kendall’s tau, Spearman’s rho and Gini’s gamma can be expressed in terms of the map [. , .]. Quite generally, the map [. , .] can be applied to construct and investigate measures of concordance.

12

Characterization of asymptotical expansions of copulas by the use of homogeneous functions

88%

Iwaniec E.

|

2009

|

tom Vol. 42, nr 3

567-579

EN

The definition, terminology and possible forms of homogeneous expansion of copulas are given. The methodology that provides homogeneous expansions with a proof of their existence is presented. Numerous examples illustrating the usage of the main theorem for valuation of the expansions are indicated.

13

The testing of causal stock returns-trading volume dependencies with the aid of copulas

88%

Gurgul H. , Mestel R. , Syrek R.

|

tom 13

21-44

EN

This paper is concerned with a dependence analysis of returns, return volatility and trading volume for five companies listed on the Vienna Stock Exchange. Taking into account the high frequency data for these companies, tests based on a comparison of Bernstein copula densities using the Hellinger distance were conducted. It is worth noting that these tests can be used in general settings since there is no restrietion on the dimension of the data. The parameter which must be set up for the testing procedure is a bandwidth. It is necessary for estimation of the nonparametric copula. The paper presents some patterns of causal relationships between stock returns, realized volatility and expected and unexpected trading volume. There is linear causality running from realized volatility to expected trading volume, and a lack of nonlinear dependence in the opposite direction. The authors detected strong linear and nonlinear causality from stock returns to expected trading volume. Therefore, a knowledge of past stock returns can improve forecasts of expected trading volume. They did not find causality running in the opposite direction.

14

Spatial-serial dependency in multivariate GARCH models and dynamic copulas: a simulation study

75%

Klein I. , Kock C. , Tinkl F.

Ekonomia Menedżerska

|

2010

|

tom nr 7

43-62

EN

The serial dependency of multivariate financial data will often be filtered by considering the residuals of univariate GARCH models adapted to every single series. This is the correct filtering strategy if the multivariate process follows a so-called copula based multivariate dynamic model (CMD). These multivariate dynamic models combine univariate GARCH in a linear or nonlinear way. In these models the parameters of the marginal distribution (=univariate GARCH models) and the dependence parameter are separable in the sense that they can be estimated in two or more steps. In the first step the parameters of the marginal distribution will be estimated and in the second step the parameter(s) of dependence. To the class of CMD models belong several multivariate GARCH models like the CCC and the DCC model. In contrast the BEKK model, f.e., does not belong to this class. If the BEKK model is correctly specified the above mentioned filtering strategy could fail from a theoretical point of view. Up to now, it is not known which dynamic copula is incorporated in a BEKK model. We will show that if the distribution of the innovations (i.e. the residuals) of MGARCH models is spherical the conditional distribution of the whole MGARCH process belongs to the elliptical distribution family. Therefore estimating the dependence of a BEKK model by copulas from the elliptical family should be an appropriate strategy to identify the dependence (i.e. correlation) between the univariate time series. Furthermore we will show, that a diagonal BEKK model can be separated in its margins and a copula, but that this strategy falls short of investigating full BEKK models.

PL

Zależność w wielowymiarowych danych finansowych jest często usuwana za pomocą analizy reszt jednowymiarowych modeli GARCH zaadaptowanych do każdego pojedynczego szeregu. Ten sposób filtracji jest właściwy, jeśli proces wielowymiarowy daje się opisać za pomocą tak zwanych wielowymiarowych modeli dynamicznych (CMD) opartych na kopuli. Te wielowymiarowe modele dynamiczne łączą jednowymiarowe modele GARCH w sposób liniowy lub nieliniowy. W modelach tych parametry rozkładów brzegowych (=jednowymiarowe modele oraz parametry) oraz zależności są separowane w takim sensie, że mogą być estymowane w dwóch lub więcej krokach. W pierwszym kroku są estymowane parametry rozkładu brzegowego, a w kroku drugim estymuje się parametr bądź parametry zależności. Do klasy modeli CMD należy kilka modeli wielowymiarowych typu GARCH, jak na przykład CCC oraz model DCC. W przeciwieństwie do wymienionych modeli model BEKK nie należy do tej klasy. Jeśli model BEKK jest prawidłowo wyspecyfikowany, to wspomniana strategia filtracji z teoretycznego punktu widzenia może zawodzić. Dotąd nie jest wiadomo, która kopula dynamiczna jest włączona do modelu BEKK. Pokażemy, że o ile rozkład prawdopodobieństwa innowacji (tzn. reszt) modeli MGARCH jest rozkładem sferycznym, to rozkład warunkowy całego MGARCH należy do eliptycznej klasy rozkładów prawdopodobieństwa. Dlatego estymacja zależności modelu BEKK za pomocą kopul należących do eliptycznej rodziny rozkładów powinna być właściwą strategią identyfikacji zależności (tzn. korelacji) pomiędzy jednowymiarowymi szeregami czasowymi. Ponadto pokażemy, ze model diagonalny BEKK może być rozdzielony na swoje modele brzegowe oraz stosowne kopule. Jednakże ta strategia nie jest wystarczająca w badaniu całkowitych (niediagonalnych) modeli typu BEKK.

15

Zastosowanie kopuli w zadaniu minimalizacji wartości zagrożonej portfela

75%

Lach A.

Optimum. Studia Ekonomiczne

|

2015

|

tom 2(74)

PL

W artykule zastosowano wybrane kopule w zadaniu minimalizacji wartości zagrożonej (VaR) portfeli w okresach charakteryzujących się odmiennym typem trendu. Rozkłady empiryczne stóp zwrotu z akcji 10 spółek wchodzących w skład indeksu WIG20 połączono kopulami Gaussa, t-Studenta, Claytona, Franka, Gumbela i odwróconą Gumbela. Symulacje z tak otrzymanych rozkładów wielowymiarowych stanowiły podstawę do utworzenia portfeli minimalizujących wartość zagrożoną. Jakość VaR, wyliczoną dla pozycji krótkiej i długiej, oceniono testem Kupca. Wartość zagrożona została poprawnie wyznaczoną dla rozkładów utworzonych za pomocą: dwóch kopuli archimedesowych uwzględniających zależność w dolnym ogonie (Claytona i odwróconej Gumbela), jednej kopuli z symetryczną zależnością w ogonach (t-Studenta) oraz jednej kopuli nie mającej zależności w ogonach (Gaussa).

EN

In the paper, selected copulas are applied in the task of minimizing the value at risk (VaR) of portfolios in the periods characterized by different types of trend. Empirical distributions of returns on 10 companies listed on WIG20 index are combined with Gaussian, t-Student, Clayton, Frank, Gumbel, and rotated Gumbel copulas. Simulations from thus obtained multivariate distributions are the basis for minimizing the VaR of portfolios. The quality of the VaR, calculated for both short and long positions, are assessed with the Kupiec test. The value at risk is properly set for joint distributions created with the following copulas: two Archimedean copulas with lower tail dependence (Clayton and rotated Gumbel), one copula with symmetric dependence in tails (t-Student), and one copula with no tail dependence (Gaussian).

16

Kopule i przyczynowość w badaniach związków pomiędzy zmiennymi finansowymi wybranych spółek z DAX

75%

Gurgul H. , Mestel R. , Syrek R.

|

tom nr 3

7-20

PL

W artykule rozważono zależności równoczesne i przyczynowe pomiędzy stopami zwrotu, ich zmiennością i wielkością obrotów. Badania zostały przeprowadzone dla wybranych z DAX największych spółek giełdowych. Stwierdzono za pomocą kopul brak istotnej statystycznie przyczynowości pomiędzy stopami zwrotu i wielkością obrotów. Jednocześnie w prawie wszystkich wypadkach stwierdzono istnienie przyczynowości obustronnej pomiędzy stopami zwrotu i ich zmiennością. We wszystkich wypadkach stwierdzono istnienie zależności jednostronnej od zmienności stóp zwrotu do wielkości obrotów. Nie stwierdzono odwrotnej zależności. Ten ostatni wynik świadczy o tym, że wzrastająca zmienność stóp zwrotu może być symptomem zbliżającej się wzmożonej aktywności handlowej inwestorów, dotyczącej akcji danej spółki.

EN

In the paper contemporaneous and dynamic relations between stock returns, stock returns volatility and trading volume for selected German companies quoted in DAX since 1994 are considered. The authors found out by mean of copulas significant contemporaneous pairwise dependences between these market variables. Dynamic relations were proved statistically by mean of Granger causality concept. The linear and nonlinear causality tests confirmed no causality between stock returns and trading volume in both directions. The performed computations are reason for claim that between stock returns and stock returns volatility might be a feedback. There is in all cases a strong causality from volatility to trading volume, but not in opposite direction.

17

The theorems characterizing the positive quadrant dependence models and Lancaster distributions

75%

Furmańczyk K.

|

2007

|

tom Vol. 40, nr 4

951-962

EN

In this paper, we consider the characterizing theorems for positive quad-rant dependence model with bivariate variables (X, Y) and Lancaster bivariate probabil-ity distributions. They arę characterized by the marginal distributions and the regression functions E(Y \ X = x), E(X \ Y = y), for some simple model, and, by E(Yi \ X = x), E(Xi | Y = y), i = 1,2,..., for generalizations. In this paper, some connections with copulas, has been also considered.

18

Status gramatyczny predykatywnych SZKODA , WSTYD , ŻAL raz jeszcze

71%

Przepiórkowski A.

|

tom 39

85-110

EN

The apparently nominal forms szkoda ‘pity’, wstyd ‘shame’, żal ‘regret’, when used predicatively, have been analysed either as ‘quasi-verbs’ (inflecting only for tense and mood), or as adverbs, or as nouns. The author recalls and reinforces arguments against their verbal analysis, and shows that such forms are categorially ambiguous. In their adverbial guise, they may be modified by other adverbs, they do not agree with the copula, they may co-occur with a dative experiencer, and they may occur in other predicative constructions, apart from copular constructions. In their nominal guise, they may be modified by adjectives, they agree with the copula, they do not easily combine with a dative experiencer, and they do not occur in other predicative constructions. The author also argues that this categorial ambiguity is correlated with the two copular constructions in Polish: one involving the purely verbal copula być ‘be’ and the other involving the so-called ‘pronominal’ copula to (być).

PL

Pierwszym celem niniejszego artykułu jest potwierdzenie, że predykatywne szkoda, wstyd, żal nie są czasownikami niewłaściwymi. Dwa inne poglądy na temat statusu jednostek typu szkoda mówią, że są to przysłówki lub rzeczowniki. Autor pokazuje, że oba są prawdziwe: omawiane jednostki są kategorialnie niejednoznaczne, przy czym istnieje szereg testów pozwalających odróżnić użycia adwerbialne od użyć nominalnych. Przedstawia także argumenty za tym, że kategoria gramatyczna predykatywnych użyć omawianych jednostek skorelowana jest z typem konstrukcji łącznikowej, w której występują: formy przysłówkowe z łącznikiem być, natomiast formy rzeczownikowe – z łącznikiem to.

19

Dependence of Stock Returns in Bull and Bear Markets

63%

Dobric J. , Frahm G. , Schmid F.

|

2013

|

tom 1

94-110

EN

Despite of its many shortcomings, Pearson’s rho is often used as an association measure for stock returns. A conditional version of Spearman’s rho is suggested as an alternative measure of association. This approach is purely nonparametric and avoids any kind of model misspecification. We derive hypothesis tests for the conditional rank-correlation coefficients particularly arising in bull and bear markets and study their finite-sample performance by Monte Carlo simulation. Further, the daily returns on stocks contained in the German stock index DAX 30 are analyzed. The empirical study reveals significant differences in the dependence of stock returns in bull and bear markets.

20

The structure of contemporaneous price-volume relationships in financial markets

63%

Gurgul H. , Syrek R.

Managerial Economics

|

2013

|

tom nr 14

39--60

EN

The main goal of this paper is an examination of the interdependence stuctures of stock returns, volatility and trading volumes of companies listed on the CAC40 and FTSE100. The authors establish that the mean values of respective measures are different on the markets under study. In general, they are larger for equities from CAC40 than from FTSE100. The Mixture of Distributions Hypothesis with long memory is rejected for about 70 % of stocks from both markets. Additionally fractional cointegration was tested. The lack of fractional cointegration, suggests a rejection of the last variant of MDH in all cases, i.e. the time series under study do not exhibit common long-run dependence. The analyzed time series are not driven by a common information arrival process with long memory. Correlation between volatility and trading volume is present for all the stocks of companies from these markets. The mixtures of rotated copulas and Kendall correlation coefficient allowed the checking of extreme return-volume dependence structures. The empirical results reflect significant dependencies between high volatility and high trading volume. In general, the dependence structures of stock returns and trading volume are different. In the case of CAC40 companies high trading volume is not correlated as frequently with high stock returns as with low stock returns. For companies listed on the FTSE100 high stock returns are mostly related with high trading volume.

PL

Głównym celem artykułu jest znalezienie zależności pomiędzy stopami zwrotu, ich zmiennością oraz wielkością obrotów dla spółek należących do indeksów CAC40 i FTSE100. Autorzy ustalili, że średnie miary zależności na obu badanych rynkach różnią się istotnie. Przeważnie są one większe w przypadku spółek notowanych w indeksie CAC40 aniżeli w przypadku spółek z indeksu FTSE100. Badania empiryczne dają podstawę do odrzucenia ok. 70% akcji z obu rynków hipotezy o mieszance rozkładów (MDH) w przypadku dla wszystkich szeregów czasowych w wersji z długą pamięcią. Dodatkowo przetestowano istnienie kointegracji ułamkowej pomiędzy badanymi chrakterystykami akcji. Stwierdzono brak istotnej statystycznie kointegracji ułamkowej, co sugeruje konieczność odrzucenia ostatniego wariantu MDH odnośnie do badanych szeregów czasowych we wszystkich przypadkach. Świadczy to o tym, że nie wykazują one wzajemnej zależności długoterminowej. Tak więc analizowane szeregi czasowe nie są generowane przez wspólny proces napływu informacji z długą pamięcią. Występuje korelacja pomiędzy zmiennością stóp zwrotu a wielkością obrotów akcji wszystkich spółek z rozważanych rynków. Badania pozwoliły na ustalenie, że mieszanka obróconych kopuł oraz współczynnik korelacji Kendalla umożliwiły sprawdzenie zależności pomiędzy ekstremalnymi stopami zwrotu i ekstremalną wielkością obrotów. Wyniki empiryczne odzwierciedlają istotne zależności pomiędzy wysoką zmiennością stop zwrotu i wysoką wielkością obrotów. Jednak struktury zależności w przypadku poszczególnych spółek różnią się istotnie. W przypadku spółek z CAC40 wysokie wielkości obrotów akcjami nie są tak często skorelowane z wysokimi stopami zwrotu jak z niskimi. Natomiast w przypadku FTSE100 wysokie stopy zwrotu są przeważnie skorelowane z wysokimi wielkościami obrotów.