ARCH Models Efficiency Evaluation in Prediction and Poultry Price Process Formation

اقتصاد و توسعه کشاورزی

Article 1, Volume 30, Issue 2, June 2016, Pages 80-87   

Document Type: Research Article

DOI: 10.22067/jead2.v30i2.32388

Authors

B. Fakari Sardehae^* ; M. Gorbani

Ferdowsi University of Mashhad

Abstract

Introduction: Poultry is an important commodity for household consumption. In recent years, price fluctuation for this commodity has caused an uncertain condition for consumers and poultry prices over the past two years has changed a lot. This has caused many changes and uncertainty in a purchase decision. Analysis of changes and volatility modeling can be a great help to predict the poultry prices and great facilities in creating appropriate policies in future. The prices of staples such as poultry consumption basket is highly variable because much of the protein is necessary for daily energy are supplied in this way to households. So when the price of chicken which has been changed over the past two years and has always been in the press and media attention, has been selected in this study. Fluctuations in price of chicken have caused a surge in consumer expectations and contributed in volatility of chicken price.
Materials and Methods: In this study ARCH models have been used for daily price of poultry of Iran’s market and this was investigated for2012-13and2013-14.BecauseARCH models can model the impact of heterogeneous variance over time in time series data then the variance of time series, which is limited in time, has no time limit. Many time series are more complex than a linear patterns, thus, non-linear models are of particular importance in Economic Sciences and Econometrics. Accordingly, Engle presented that ARCH model can model the heterogeneous variance components of the error term. That is a disturbing element and modeling can help to examine and explore the relationship between the components can be found disturbing. Basically, these models fit the data to a cluster and periodic oscillations with high volatility and low volatility associated with the period. In this study, we used several different models like ARCH, GARCH, IGARCH, and TGARCH. The distribution of the error term of the model also followt-student distribution. This study shows that the heterogeneous variance exists in error term and indicated by LM-test.
Results and Discussion: Results showed that stationary test of the poultry price has a unit root and is stationary with one lag difference, and thus the price of poultry was used in the study by one lag difference. Main results showed that ARCH is the best model for fluctuation prediction. Moreover, news has asymmetric effect on poultry price fluctuation and good news has a stronger effect on poultry price fluctuation than bad news and leverage effect doesnot existin poultry price. Moreover current fluctuation does not transmit to future. One of the main assumptions of time series models is constant variance in estimated coefficients. If this assumption has not been, the estimated coefficients for the correlation between the serial data would be biased and results in wrong interpretation. The results showed that ARCH effects existed in error terms of poultry price and so the ARCH family with student t distribution should be used. Normality test of error term and exam of heterogeneous variance needed and lack of attention to its cause false conclusion. Result showed that ARCH models have good predictive power and ARMA models are less efficient than ARCH models. It shows that non-linear predictions are better than linear prediction. According to the results that student distribution should be used as target distribution in estimated patterns.
Conclusion: Huge need for poultry, require the creation of infrastructure to response to demands. Results showed that change in poultry price volatility over time, may intensifies at anytime. The asymmetric effect of good and bad news in poultry price leading to consumer's reaction. The good news had significant effects on the poultry market and created positive change in the poultry price, but the bad news did not result insignificant effects. In fact, because the poultry product in the household portfolio is essential, it should not fluctuate. When poultry imports decline, as well as the dependence of the poultry price to world prices declines therefore lower fluctuations of world prices are transmitted to domestic prices. Expanding poultry farms, cold storage and balance the raw materials market, would lead to less fluctuations in the poultry price industry and can be effective.

Keywords

POULTRY PRICE; QQ PLOT; ARCH-M; PGARCH; TGARCH

References

1- Benavides G. 2009. Price volatility forecasts for agricultural commodities: an application of volatility models, option implies and composite approaches for futures prices of corn and wheat. Journal of Management, Finance and Economics, 3(2): 40-59.

2- Bollerslev T. 1986. Generalized autoregressive conditional Economic Review, Federal Reserve Bank of Kansas City, 79 (3): 27-38.

3- Breusch T.S. 1979. Testing for autocorrelation in dynamic linear models. Australian Economic Papers, 17: 334–355.

4- Chambers J. M., Cleveland W. S., Kleiner B., and Tukey P. A. 1983. Graphical methods for data analysis. Murray Hill, NJ: Wadsworth & Brooks/Cole Publishing Company.

5- Chand S., Kamal Sh., and Ali I. 2012. Modeling and volatility analysis of share prices using ARCH and GARCH models. World Applied Sciences Journal, 19 (1): 77-82.

6- Cleveland W. S. 1994. The elements of graphing data, Summit, NJ: Hobart Press.

7- Ding C. W., Granger J., and Engle R. 1993. A long memory property of stock market returns and a new model. Journal of Empirical Finance, 1: 83–106.

8- Enders W. 2010. Applied econometric time series. 3nd ed. Wiley. Alabama.

9- Engle R. 1982. Autoregressive conditional heteroscedasticity with estimates of the variance of U.K. inflation. Econometrica, 50:987–1008.

10- Engle R., and Bollerslev T. 1986. Modeling the persistence of conditional variances. Econometric Reviews, 5: 1–50.

11- Engle R., David M.L., and Russell P. 1987. Estimating time varying risk premia in the term structure: the ARCH-M model. Econometrica, 55: 391–407.

12- Gahremanzade M., and Aref eshgi T. 2013. Modeling asymmetric volatility in the market prices of poultry meat Tehran Province. Journal of Agricultural Economics and Development, 27 (2): 134-143.

13- Glosten L. R., Jaganathan R., and Runkle D. 1993. On the relation between the expected value and the volatility of the normal excess return on stocks, « Journal of Finance, 48: 1779–1801.

14- Godfrey L. G. 1988. Specification tests in econometrics. Cambridge: Cambridge University Press.

15- Grasa A.A. 1989. Econometric model selection a new approach, Dordrecht: Kluwer Academic Publishers.

16- Homaun A., Mohammadi H., and Keshtkar A. 2010. Evaluation of predictive models of stock market indices in Iran. Journal of Research and Economic Policies, 18 (56): 95-112.

17- Lawrance A.J. 2011. Volatile ARMA Modelling of GARCH Squares. Central European Journal of Economic Modelling and Econometrics, 2: 195-203.

18- McKenzie M., Mitchell H., Brooks R., and Faff R. 2001. Power ARCH modelling of commodity futures data on the London Metal Exchange. The European Journal of Finance 7, 22–38.

19- Mohammadi H., Farajzade Z., Dehbashi V., Shahraki A., and Ansarinik H. 2013. Select price modeling of dairy products. Journal of Agricultural Economics and Development, 21(81): 101-129.

20- Nelson D. B. 1991. Conditional heteroskedasticity in asset returns: a new approach. Econometrica, 59: 347–370.

21- Noureldin D., Shephared N., and Shephard K. 2012. Multivariate Rotated ARCH Models. Working Paper, Department of Economics, University of Oxford,& Oxford-Man Institute.

22- O.Donnell J., and Rayner V. 2007. Imposing necessary conditions for stationarity on ARCH and GARCH models. Journal of Econometrics 122(1): 27-48.

23- Schwert W. 1989. Stock volatility and crash of ‘87. Review of Financial Studies, 3: 77–102.

24- Taylor S. 1986. Modeling financial time series, New York: John Wiley & Sons.

25- Trenca I., and Mihail C. 2011. Modeling Romanian exchange rate evolution with garch, tgarch, garch- in mean models. The Annals of the University of Oradea. Economic Sciences, 1: 299-305.

26- Zakoïan J. M. 1994. Threshold heteroskedastic models. Journal of Economic Dynamics and Control, 18: 931-944.