Resumen de The causal modelling on equity market innovations: fit or forecast?

Jin Woong Kim, David A. Bessler

• This article considers innovation accounting using an Error Correction Model and Directed Acyclical Graphs (DAGs) on 10 Global Industry Classification Standard (GICS) aggregations of daily US equity values over the years 1995 to 2003. The GICS equity aggregates studied are: Consumer Discretionary, Consumer Staples, Energy, Financials, Health Care, Industrials, Information Technology, Materials, Telecommunication Services and Utilities. DAGs are constructed from ex post and ex ante forecast innovations from an error correction model fit to these data. The DAG constructed from ex ante forecast innovations is consistent with the DAG from ex post fit innovations, a result that supports innovation accounting based on DAGs using ex post innovations.