Search

We explore properties of asymmetric generalized autoregressive conditional heteroscedasticity (GARCH) models in the threshold GARCH (GTARCH) family and propose a more general Spline-GTARCH model, which captures high-frequency return volatility, low-frequency macroeconomic volatility as well as an asymmetric response to past negative news in both autoregressive conditional heteroscedasticity (ARCH) and GARCH terms.

While the Bank of Canada's inflation-control target is specified in terms of the rate of increase in the total consumer price index, the Bank uses a measure of trend or "core" inflation as a short-term guide for its monetary policy actions. When the inflation targets were renewed in May 2001, the Bank announced that it was adopting a new measure of core inflation. This measure excludes the eight most volatile components of the CPI and adjusts the remaining components for the effect of changes in indirect taxes. In this article, the author discusses the definition of the new measure of core inflation and describes some of its advantages relative to the previous measure. He notes that the new measure has a firmer statistical basis, has a better correspondence with economic theory, and does a better job of predicting future changes in overall inflation. While the new measure has these advantages, the Bank will continue to monitor a broad range of indicators when assessing the likely future path for inflation.

Commodity prices are once again making headlines. Some commodity prices, such as those for copper and cattle, have reached record highs; others are rising quickly and approaching previous peaks.

We propose a macroeconomic model with a nonlinear Phillips curve that has a flat slope when inflationary pressures are subdued and steepens when inflationary pressures are elevated. Our model can generate more sizable inflation surges due to cost-push and demand shocks than a standard linearized model when inflation is high.

Following the recent financial crisis, major central banks have introduced several types of unconventional monetary policy measures, including liquidity and credit facilities, asset purchases and forward guidance. To date, these measures appear to have been successful. They restored market functioning, facilitated the transmission of monetary policy and supported economic activity. They have potential costs, however, including challenges related to the greatly expanded balance sheets of central banks and the eventual exit from these measures, as well as the vulnerabilities that can arise from prolonged monetary accommodation.

A low level of the neutral rate of interest increases the likelihood that a central bank’s policy rate will reach its effective lower bound (ELB) in future economic downturns. In a low neutral rate environment, using an extended monetary policy toolkit including forward guidance helps address the ELB challenge. Using the Bank’s Terms-of-Trade Economic Model, we assess the benefits and limitations of a state-contingent forward guidance implemented within a flexible inflation targeting framework.

In recent years, the Bank has put renewed emphasis on analyzing monetary variables and on developing models that incorporate money as an active part of the transmission mechanism. In this article, Dinah Maclean describes how the monetary aggregates are used in the formulation of monetary policy analysis at the Bank, outlining the key tools and models used. The most important money-based model currently in use is the M1-VECM. In this model, deviations in the money supply from the long-term demand for money cause changes in inflation. The author briefly describes the "active-money" paradigm underlying this model and explains the key equations within it. Other simpler empirical models are also outlined, including single-equation indicator models for output based on the narrow aggregates, a neural network, and a model based on the broader aggregate M2++. A detailed technical annex provides details on model equations and coefficient values.

This paper considers the problem of estimating a linear model between two heavy-tailed variables if the explanatory variable has an extremely low (or high) value. We propose an estimator for the model coefficient by exploiting the tail dependence between the two variables and prove its asymptotic properties.

We present the annual update of the Bank of Canada staff estimates for global potential output growth. These estimates served as key inputs to the analysis supporting the April 2026 Monetary Policy Report.

Using Canadian matched employer-employee data, we show that working hours of different workers are gross complements in production rather than perfect substitutes, as is typically assumed by macroeconomic models of production.