Testing for Linear and Nonlinear Granger Causality in the Stock Price‐Volume Relation

Abstract

Linear and nonlinear Granger causality tests are used to examine the dynamic relation between daily Dow Jones stock returns and percentage changes in New York Stock Exchange trading volume. We find evidence of significant bidirectional nonlinear causality between returns and volume. We also examine whether the nonlinear causality from volume to returns can be explained by volume serving as a proxy for information flow in the stochastic process generating stock return variance as suggested by Clark's (1973) latent common-factor model. After controlling for volatility persistence in returns, we continue to find evidence of nonlinear causality from volume to returns. THIS ARTICLE USES LINEAR and nonlinear Granger causality tests to examine the dynamic relation between daily aggregate stock prices and trading volume. Causality tests can provide useful information on whether knowledge.of past stock price movements improves short-run forecasts of current and future movements in trading volume, and vice versa. We provide empirical support for the argument made by Gallant, Rossi, and Tauchen (1992) that more can be learned about the stock market through studying the joint dynamics of stock prices and trading volume than by focusing only on the univariate dynamics of stock prices. In addition, our analysis produces stylized facts about how daily aggregate stock prices and trading volume are intertemporally related, which may prove useful to future theoretical and empirical work on the stock market.

Stock Returns and the Volatility of Liquidity

“…17 Several papers, including Hasbrouck (1991), Hiemstra and Jones (1994), Chordia, Roll, and Subrahmanyam (2001), Chordia, Sarkar, and Subrahmanyam (2005a), and Chordia, Sarkar, and Subrahmanyam (2005b, have studied the time-series relation between several measures of liquidity, trading activity, and returns. However, they do not analyze the causality from liquidity to trading volume.…”

Causality Between Us Economic Policy and Equity Market Uncertainties: Evidence from Linear and Nonlinear Tests

“…This is because the linear test is only sensitive to causality in the conditional mean and may not be sufficient to detect nonlinear effects on the conditional distribution (Baek and Brock 1992). Hiemstra and Jones (1994) also noted that traditional linear Granger causality test have low power in detecting certain kinds of nonlinear relations. Higher order structure, such as conditional heretoskedasticity, is also often ignored Panchenko 2005, 2006).…”

“…Therefore we turn to nonlinear tests. Using Hiemstra and Jones (1994), Diks and Panchenko (2006), and Kyrtsou and Labys (2006) symmetric test, we observe a stronger predictive power from EMU to EPU than from EPU to EMU. (2006) test, we find no evidence of positive predictive power from EPU to EMU.…”

“…Therefore, we perform parameter stability tests on the estimated full sample VAR. Subsequently, we test for causality using nonlinear methods of Hiemstra and Jones (1994), Diks and Panchenko (2006), and Kyrtsou and Labys (2006), Sato et al (2007) timevarying causality and Balcilar et al (2010) sub-sample rolling window bootstrap causality tests. This paper makes contribution to the existing literature.…”

The Testing of Causal Stock Returns-Trading Volume Dependencies with the Aid of Copulas

“…The concept by Hiemstra and Jones [29] improves the small-sample properties of the causality test and relaxes the assumption that the series to which the test is applied are i.i.d. The authors conducted some Monte Carlo simulations and proved the robustness of their test for the presence of structural breaks in the series.…”