Greg Tkacz - Latest

• A Consistent Bootstrap Test for Conditional Density Functions with Time-Dependent Data

  Staff Working Paper 2001-21 Fuchun Li, Greg Tkacz

  This paper describes a new test for evaluating conditional density functions that remains valid when the data are time-dependent and that is therefore applicable to forecasting problems. We show that the test statistic is asymptotically distributed standard normal under the null hypothesis, and diverges to infinity when the null hypothesis is false.

  Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods JEL Code(s): C, C1, C12, C15, E, E3, E37

• Evaluating Factor Models: An Application to Forecasting Inflation in Canada

  Staff Working Paper 2001-18 Marc-André Gosselin, Greg Tkacz

  This paper evaluates the forecasting performance of factor models for Canadian inflation. This type of model was introduced and examined by Stock and Watson (1999a), who have shown that it is quite promising for forecasting U.S. inflation.

  Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods, Inflation and prices JEL Code(s): C, C3, C32, E, E3, E37

• Evaluating Linear and Non-Linear Time-Varying Forecast-Combination Methods

  Staff Working Paper 2001-12 Fuchun Li, Greg Tkacz

  This paper evaluates linear and non-linear forecast-combination methods. Among the non-linear methods, we propose a nonparametric kernel-regression weighting approach that allows maximum flexibility of the weighting parameters.

  Content Type(s): Staff research, Staff working papers Topic(s): Econometric and statistical methods JEL Code(s): C, C1, C14, C5, C53, E, E2, E27