Printer Friendly

A possible trend of option on futures in Romanian capital market.


The whole financial literature and theory is based on fundamental hypothesis regarding the possible trends of financial markets, developed through stochastic methodologies. The evolution of the economics phenomena including the capital markets transactions too, under the impulse of exogenous factors that generate discontinuous effects. Modeling of such phenomena can be achieved by stochastic models. This research aims to highlight, based on a stochastic model for forecasting, possible trends of evolution of the options transactions in the capital market in Romania.


To estimate the volume of trading options on futures contracts evolution in the SIBEX, we chose the Box-Jenkins procedure (Pecican, 1994), which is justified to aim our goal, because:

* There is a large enough number of terms in chronological series so autocorrelation coefficients and parameters that will lead to the stability

* The data used in research presents the typical of a random process

* Series of values in research does not show trend, including fluctuant issues demonstrated in our previous work.

2.1 Getting stationary series

To achieve its goals, the research starts from a database, synthesized in the Table. 1, which includes the calculated values of the indices of change in volume of trading options on futures contracts for the period of time that were traded options on futures contracts in the capital market in Romania.


Graphic representation of figure 1 is indicative of a lack of the trend belonging to the series analyzed; in order to justify a further stationed the initial series of time. To station the time series means to do the differentiation of order 1, leading us to develop table 2. After realizing the stationed time series, Box-Jenkins procedure allows establishing, based on intuition expert, a representative batch for testing and application of stochastic forecasting model of this phenomenon. Thus, regarding the fact that the options on the futures began trading in 1998 in Romania, the first index-based mobile that was likely to be determined matched trading volume growth in 1999 compared to 1998. Obviously, such growth was the most spectacular of all the time initially considered, but did not believe that such value is representative of our science. Fact that we considered as representative for conducting research mobile processing indices change the volume of trading in the 2001-2008, eliminating the extreme values of 1999 and 2000.

2.2 Aprioristic identification of a stochastic model



Such research objective is achieved through using Box--Jenkins procedures, which allows choosing a stochastic model based on a two of tree criteria (Andrei, 2004):

a. The analyze of the graphic representation of the autocorrelation coefficients (rk), presented in figure 3.

b. Comparative analysis of the coefficients of autocorrelation and for partial autocorrelation.

c. Average possibilities evolving phenomenon while taking into account the economic particularities, economic situation and changes in exogenous variables of the past.

Taking into account these criteria were made preliminary estimations of the autocorrelation ([r.sub.k]) and partial autocorrelation ([c.sub.k]) coefficients, where the lag k understand the time series that we modeling it (Ho S.L. et al., 2002).

Partial autocorrelation coefficients ck, could be calculate through the Yule-Walker equations, which put about autocorrelation coefficients, previously calculated, with partial autocorrelation coefficients that has to be determined. To verify the stationary characteristic of the time series, we have to determine the proportion of the autocorrelation coefficients in the confidence interval [-2 [[??].sub.rk]; 2[[??].sub.rk]]. By performing the calculations that determine the confidence interval [-0.64, 0.64] we found that previously determined values of the autocorrelation coefficients [r.sub.k] are within this interval, which means that the series has a random nature, which justifies, as specified in Box-Jenkins procedure, the choose of such a stochastic model for determining the possible variants of the evolution of the phenomenon investigated. We consider as the best model ARIMA (1, 1, 1), an autoregressive model of mobile average by order 1. In the case of stochastic models that include average furniture, the first stage of calculation, for simplicity, it is possible to remove the media, in our case denoted by. [bar.X]. Thus, the model becomes ARMA(1.1). Verification of the model before its use for forecasts implies the analysis between the graphic representation of the autocorrelation developed for X't generated by the model adopted and values obtained by stationed model (Lim, 2002). If the initial graphic, used the stage of specification, the empirical values stationed [X.sub.T] and the graphic of autocorrelation coefficients adjust an apparent similarity, we believe that the model is valid.


In order whit our objectives, the prognoses development is based on the mathematical equation, presented in relations (1) and (2). Including the dates obtained previously, relations (1) and (2) allows us to find projected values for the years 2009, 2010, 2011 and 2012 of the indices of the trading volume of options on futures.


Results of such predictions are summarized in figure 4.

But, because such forecast model it had to include in calculation for reaching the final evaluation also the trend, which aprioristic were ignored, therefore it is necessary to perform a reverse calculation that led to the removal trend. In fact the values obtain are: [X.sub.2009] = 0.8989, [X.sub.2010] = 0.69683; [X.sub.2011] = 0.50723; [X.sub.2012] = 0.31525.


Data obtained through the Box-Jenkins model, which were applied to develop index forecasting for trading volume of options on futures contracts, tend to show a decrease in the value question. In fact, capital market in Romania, in the context of the global financial crises, will host a decrease in volume of transactions in options on futures contracts. Starting from this point of view, the present forecasting may be considered viable, especially that the data already recorded up to now show this downward trend.

The results of such a study are important in showing the real perception in Romanian financial medium of a very sophisticated financial tool, the option on futures contract, leading us to draw a possible realistic perspective of the option market in Romania. The decreasing trend which we determined are in totally correspondence with the present global financial crises, but, because the options are derivatives in direct connection whit risk management, the calculated forecast are explained by the low notoriousness of the instrument by the potential Romanian investors

Obviously there are limitations of the present research consisting in the pour number .of iteration made in the present methodology. But, the next research will improve this deficiency and we will try to modulate a correlation between option and future volume trading and the level of economic development in Romanian Financial System.


Andrei, T. (2003). Statistics and econometrics, Economics Publisher, ISBN 973-590-764, Bucharest

Corduneanu C. & Iovu, L.R (2008). Steps in the Development of the Romanian Financial System and the Correlation with the Level of Economic Growth, Timisoara Journal of Economics, No.1/2008, ISSN 1844-7139, 12-17

Ho S.L.; Xie M. & Goh, T.N. (2002). A comparative study of neuronal network and Box-Jenkins ARIMA modeling in time series prediction, in Computers &Industrial Engineering, Volume 42, Issues 2-4, 371-375

Lim, C. & McAgeer (2002). Time series forecast of international travel demand for Australia, in Tourism Management, Volume 23, Issues 4, 389-396

Pecican, E.S.(1994). Econometrics, All Publisher, ISBN 9739156-25-8, Bucharest

Summa, J.F. (2004). Trading Against the Crowd, Publisher Wiley Trading, ISBN 0-471-47121-6, New Jersey
Tab. 1. Series of statistical modeling

 Index of option
Years t on futures volume

1999 1 114.4
2000 2 3.07
2001 3 1.15
2002 4 1.25
2003 5 0.29
2004 6 0.12
2005 7 5.12
2006 8 3.15
2007 9 0.95
2008 10 1.15

Tab. 2 The input data in research

Years Index ([X.sub.t]) [X.sub.t] [bar.X] = V

2001 1.15 -1.92 -1,68
2002 1.25 0.1 0,34
2003 0.29 -0.96 -0,72
2004 0.12 -0.17 0,07
2005 5.12 5 5,24
2006 3.15 -1.97 -1,73
2007 0.95 -2.2 -1,96
2008 1.15 0.2 0,44
COPYRIGHT 2009 DAAAM International Vienna
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2009 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Vancea, Smaranda; Horja, Monica Ioana; Avram, Eeonora Laura; Ignat, Andreea Brindusa
Publication:Annals of DAAAM & Proceedings
Article Type:Report
Geographic Code:4EXRO
Date:Jan 1, 2009
Previous Article:A simple framework for dynamic partial reconfiguration.
Next Article:Using SAP NetWeaver to implement a new authorization concept based on qualifications and physical connection through RFID.

Terms of use | Privacy policy | Copyright © 2020 Farlex, Inc. | Feedback | For webmasters