Measuring Potential Output at the Bank of Canada: The Extended Multivariate Filter and the Integrated Framework

Estimating potential output and the output gap - the difference between actual output and its potential - is important for the proper conduct of monetary policy. However, the measurement and interpretation of potential output, and hence the output gap, is fraught with uncertainty, since it is unobservable. It is therefore important that we continually expand and improve upon existing models, and innovate by testing new approaches and incorporating them into the analysis of potential output and the output gap. Within this context, this paper first provides an assessment of the extended multivariate filter (EMVF), which the Bank has used since the late 1990s to come up with a baseline measure of the output gap. It is determined that the EMVF has several limitations that need to be addressed. Consequently, a modified version of the EMVF incorporating revised conditioning information is presented. In addition, a newly developed methodology, the integrated framework (IF), provides a separate analysis of trend labour input and trend labour productivity, and in doing so accounts for more long-term structural changes in the economy. While neither of these approaches is perfect, and both have limitations, they represent improvements over the conventional method. The paper also outlines how the modified EMVF, the IF, and information from the Bank’s Business Outlook Survey and other sources are used to come up with an estimate of the current output gap and the future growth rate of potential output.