Asymmetric GARCH models on price volatility of agricultural commodities

被引：0
作者：
Tirngo Dinku
Gardachew Worku
机构：
[1] Bahir Dar University, Bahir Dar
[2] Injibara University, Injibara
来源：
SN Business & Economics | / 2卷 / 11期
关键词：
Agricultural commodities; EGARCH; Leverage effect; TGARCH; Volatility;
D O I：
10.1007/s43546-022-00355-7
中图分类号：
学科分类号：
摘要：
This study aimed to estimate the best-fit volatility model. To meet this objective, data on the retail prices of agricultural commodities recorded from 2010 to 2020 from three regions and one city administration were collected from the central statistics agency (CSA). The researcher used asymmetric generalized autoregressive conditional heteroskedasticity models for estimating the volatility of price returns of agricultural commodity prices in Ethiopia. Asymmetric GARCH family models, specifically threshold GARCH, and exponential GARCH were applied to analyze the time-varying volatility of price returns of cereals, pulses, oilseeds, species, and root crops. The data analysis results revealed that the EGARCH model with normal distribution assumption of residuals was a best-fitted model for “teff”, “maize”, niger, “onion”, “potato”, and “red pepper”, and the TGARCH was a better-fitted model for the price volatility of “sorghum”, “barley”, and “beans”. However, the finding showed that no model was found to be the best fit for wheat price return in the sampled periods. In general, the study established the presence of time-varying conditional volatility, in which the effect of today’s shock remains in the forecast of variance for many periods in the future. It also specified the existence of a leverage effect, wherein the “bad” news and the “good” news of the same magnitude could have a different effect. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2022.
引用
收藏
相关论文
共 23 条
  • [1] Abebe T.H., Woldesenbet E.G., Zeleke B.L., Statistical analysis of price volatility of agricultural commodities traded at the Ethiopian commodity exchange (ECX) Using multiplicative GARCH-MIDAS two-component model, Global Bus Rev, 23, pp. 925-945, (2020)
  • [2] Kuhe D.A., Modeling volatility of agricultural commodity food price index in Nigeria using ARMA-GARCH models, Mediterran J Basic ASci, 3, 1, pp. 55-75, (2019)
  • [3] Ayele A.W., Gabreyohannes E., Tesfay Y.Y., Macroeconomic determinants of volatility for the gold price in Ethiopia: the application of GARCH and EWMA volatility models, Glob Bus Rev, 18, 2, pp. 308-326, (2017)
  • [4] Bollerslev T., Generalized autoregressive conditional heteroskedasticity, Journal of Econometrics, 31, 3, pp. 307-327, (1986)
  • [5] Brockwell P.J., Davis R.A., Time series: theory and methods, (2009)
  • [6] Burnham K.P., Anderson D.R., A practical information-theoretic approach, Model Sel Multimodel Inference, 2, pp. 70-71, (2002)
  • [7] Agency C.S., Agricultural Sample Survey, Ethiopia, (2016)
  • [8] Engle R.F., Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation, Econometrica, 50, 4, (1982)
  • [9] Hong Y., Consistent testing for serial correlation of unknown form, Econom: J Econ Soc, 64, pp. 837-838, (1996)
  • [10] Jarque C.M., Bera A.K., A test for normality of observations and regression residuals, Int Stat Rev, 55, pp. 163-172, (1987)
123