Temporal Aggregation and Systematic Sampling Effects on Non Linear Granger Causality Tests between Trade Volume and Returns. Some Monte Carlo and Empirical Results from the Athens Stocks Exchange.

Several tests for nonlinear causality are available on the literature. In this paper we investigate the effects of temporal aggregation and systematic sampling using some well known linear and nonlinear Granger causality tests. The conducted Monte Carlo simulation experiments and the empirical applications using data from the Athens Stocks Exchange Market, show that the use of temporally aggregated and systematic sampled data can affect seriously our conclusions about the linear or nonlinear causality effects between Trade Volume and Returns