C - Mathematical and Quantitative Methods
-
-
CANVAS: A Canadian Behavioral Agent-Based Model
The Bank of Canada’s current suite of models faces challenges in addressing network effects that integrate household and firm-level heterogeneity and their behaviours. We develop CANVAS, a Canadian behavioural agent-based model to contribute to the Bank’s next-generation modelling effort. CANVAS improves forecasting performance and expands capacity for model-based scenario analysis. -
Core inflation over the COVID-19 pandemic
We assess the usefulness of various measures of core inflation over the COVID-19 pandemic. We find that Cpi-trim and CPI-median provided the best signal of underlying inflation. The favourable performance of these measures stems from their lack of reliance on historical experience, an especially valuable feature in unprecedented times. -
Private Digital Cryptoassets as Investment? Bitcoin Ownership and Use in Canada, 2016-2021
We report on the dynamics of Bitcoin awareness and ownership from 2016 to 2021, using the Bank of Canada's Bitcoin Omnibus Surveys (BTCOS). Our analysis also helps understand Bitcoin owners who adopted during the COVID-19 and how they differ from long-term owners. -
October 12, 2022
Five things we learned about Canadian Bitcoin owners in 2021
We present key findings from the 2021 Bitcoin Omnibus Survey on Canadians’ awareness and ownership of Bitcoin. Most Canadians have heard of Bitcoin, which remains primarily used as an investment. Ownership jumped in 2021, reflecting increased savings during the pandemic and greater availability of user-friendly platforms to buy Bitcoin. -
Examining recent revisions to CPI-common
Unusually large revisions to CPI-common in recent months stem from increased common movements across consumer price index components amid broad inflationary pressures. With recent revisions, CPI-common is more closely aligned with the Bank of Canada’s other two preferred measures of core inflation. However, caution is necessary when interpreting real-time estimates of CPI-common in the current environment. -
Forecasting Banks’ Corporate Loan Losses Under Stress: A New Corporate Default Model
We present a new corporate default model, one of the building blocks of the Bank of Canada’s bank stress-testing infrastructure. The model is used to forecast corporate loan losses of the Canadian banking sector under stress. -
Behavioral Learning Equilibria in New Keynesian Models
We introduce behavioral learning equilibria (BLE) into DSGE models with boundedly rational agents using simple but optimal first order autoregressive forecasting rules. The Smets-Wouters DSGE model with BLE is estimated and fits well with inflation survey expectations. As a policy application, we show that learning requires a lower degree of interest rate smoothing. -
Calculating Effective Degrees of Freedom for Forecast Combinations and Ensemble Models
This paper derives a calculation for the effective degrees of freedom of a forecast combination under a set of general conditions for linear models. Computing effective degrees of freedom shows that the complexity cost of a forecast combination is driven by the parameters in the weighting scheme and the weighted average of parameters in the auxiliary models. -
Sectoral Uncertainty
We propose a new empirical framework that jointly decomposes the conditional variance of economic time series into a common and a sector-specific uncertainty component. We apply our framework to a disaggregated industrial production series for the US economy. We identify unexpected changes in durable goods uncertainty as drivers of downturns, while unexpected hikes in non-durable goods uncertainty are expansionary.