FORECAST FOR AGRICULTURAL COMMODITY FUTURES: THE ROLE OF HIGH FREQUENCY DATA

Abstract

Realized measures of volatility based on high frequency data contain valuable information about the unobserved conditional volatility. In this paper, we use the Realized GARCH model developed by Hansen, Huang and Shek (2012) to estimate and forecast price volatility for four agricultural commodity futures. Empirical evidences, both in-sample and out-of-sample, show that the Realized GARCH model and its variants outperform the conventional volatility models that only use daily price data, such as GARCH and EGARCH. We also consider skewed student's t-distribution to account for the skewness and fat-tail in the agricultural futures prices. The empirical performances are relatively close for models using three different realized measures, as the measurement equation in the Realized GARCH model can adjust to the different realized measures to some extent.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 17 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.