Granger Causality: Lag length selection.

Consider simple G-Causality on two stationary time series vectors, each with 100+ observations. It's daily financial market time series data.

I want to know the current consensus (or nearing consensus) regarding the best method of selecting lag length. A Google search has only revealed some 1984 and 1985 papers. Scholarpedia's entry ( says that it's O.K. to minimise AIC or BIC, but no references were provided for this claim so I don't want to code that up until I get confirmation.

Or is selection based on qualitative reasoning?

Cross posted on stackexchange
Last edited: