Structural Multi-Equation Macroeconomic Models: Identification-Robust Estimation and Fit Staff Working Paper 2009-19 Jean-Marie Dufour, Lynda Khalaf, Maral Kichian Weak identification is likely to be prevalent in multi-equation macroeconomic models such as in dynamic stochastic general equilibrium setups. Identification difficulties cause the breakdown of standard asymptotic procedures, making inference unreliable. Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods, Inflation and prices JEL Code(s): C, C5, C52, C53, E, E3, E37
Simulations du ratio du service de la dette des consommateurs en utilisant des données micro Staff Working Paper 2009-18 Ramdane Djoudad The author constructs a formal analytic framework to simulate the impact of various economic shocks on the household debt-service ratio, using data from the Canadian Financial Monitor (CFM) survey. Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods, Financial stability JEL Code(s): C, C1, C15, C3, C31, D, D1, D14, E, E5, E51
Testing for Financial Contagion with Applications to the Canadian Banking System Staff Working Paper 2009-14 Fuchun Li The author proposes a new test for financial contagion based on a non-parametric measure of the cross-market correlation. The test does not depend on the assumption that the data are drawn from a given probability distribution; therefore, it allows for maximal flexibility in fitting into the data. Content Type(s): Staff research, Staff working papers Topic(s): Central bank research, Econometric and statistical methods, Financial stability JEL Code(s): C, C1, C12, G, G0, G01, G1, G15
Computing the Accuracy of Complex Non-Random Sampling Methods: The Case of the Bank of Canada's Business Outlook Survey Staff Working Paper 2009-10 Daniel de Munnik, David Dupuis, Mark Illing A number of central banks publish their own business conditions survey based on non-random sampling methods. The results of these surveys influence monetary policy decisions and thus affect expectations in financial markets. To date, however, no one has computed the statistical accuracy of these surveys because their respective non-random sampling method renders this assessment non-trivial. Content Type(s): Staff research, Staff working papers Topic(s): Central bank research, Econometric and statistical methods, Regional economic developments JEL Code(s): C, C4, C8, C81, C9, C90
Assessing Indexation-Based Calvo Inflation Models Staff Working Paper 2009-7 Jean-Marie Dufour, Lynda Khalaf, Maral Kichian Using identification-robust methods, the authors estimate and evaluate for Canada and the United States various classes of inflation equations based on generalized structural Calvo-type models. The models allow for different forms of frictions and vary in their assumptions regarding the type of price indexation adopted by firms. Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods, Inflation and prices JEL Code(s): C, C1, C13, C5, C52, E, E3, E31
Relative Prices, Trading Gains, and Real GDI: The Case of Canada Staff Discussion Paper 2009-4 Yi Zheng Treating imports as intermediate inputs to domestic production, the author adopts the translog function approach to model real gross domestic income (GDI) in Canada over the 1961–2006 period. She explores the role of price ratios, such as terms of trade and the real effective exchange rate, in explaining changes in real GDI, trade openness, trade […] Content Type(s): Staff research, Staff discussion papers Topic(s): Econometric and statistical methods, Productivity JEL Code(s): C, C4, C43, D, D3, D33, F, F1, F10, O, O4, O47
Combining Canadian Interest-Rate Forecasts Staff Working Paper 2008-34 David Bolder, Yuliya Romanyuk Model risk is a constant danger for financial economists using interest-rate forecasts for the purposes of monetary policy analysis, portfolio allocations, or risk-management decisions. Use of multiple models does not necessarily solve the problem as it greatly increases the work required and still leaves the question "which model forecast should one use?" Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods, Interest rates JEL Code(s): C, C1, C11, E, E4, E43, E47
June 17, 2008 A Tool for Assessing Financial Vulnerabilities in the Household Sector Bank of Canada Review - Summer 2008 Shubhasis Dey, Ramdane Djoudad, Yaz Terajima In this article, the authors build on the framework used in the Bank of Canada's Financial System Review to assess the evolution of household indebtedness and financial vulnerabilities in response to changing economic conditions. To achieve this, they first compare two microdata sets generated by Ipsos Reid's Canadian Financial Monitor and Statistics Canada's Survey of Financial Security. They find that the surveys are broadly comparable, despite methodological differences. This enables them to use the combined information content for the identification of the threshold value of the debt-service ratio (DSR). The article then presents an innovative framework that uses household-level microdata to simulate changes in the distribution of the DSR under various stress scenarios. The authors show how this framework can be used by analyzing the effects of two different scenarios on the distribution of the debt-service ratio and the impact on vulnerable households. This tool will enable researchers to refine their analyses of current risks to the financial health of Canadian households. The article concludes with comments on future directions for refining the Bank's analyses of household sector risk. Content Type(s): Publications, Bank of Canada Review articles Topic(s): Econometric and statistical methods, Economic models, Financial stability
Empirical Likelihood Block Bootstrapping Staff Working Paper 2008-18 Jason Allen, Allan Gregory, Katsumi Shimotsu Monte Carlo evidence has made it clear that asymptotic tests based on generalized method of moments (GMM) estimation have disappointing size. The problem is exacerbated when the moment conditions are serially correlated. Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods JEL Code(s): C, C1, C14, C2, C22
Markups in Canada: Have They Changed and Why? Staff Working Paper 2008-7 Danny Leung Many empirical studies have examined the cyclical nature of the markup ratio. Until recently, few have attempted to ascertain the changes in the markup over a longer time horizon. Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods JEL Code(s): E, E3, E31, F, F4, F41, L, L1, L11