EC315 Forecasting Method Spring 2022

Topics: VECM, Lag Length Selection, Granger Causality Test, Impulse Response Function

1. Summary Statistics

2. VAR(2) Model

1. Lag Length Selection

2. Estimate VECM

%DGDPt   = a0+ Sfi%DGDP t-i   + Spi%D FXt-i    + Sqi%DHPt-i   + + SbiD Tbillt-i    + SgiDUSTbillt-i    +

+ a1ECTt-1 + ut

1. Johansen test for number of cointegrating vectors with no constant but trend in the CE.

Johansen (trace) test for Rank(P) = 0

H0: r = 0                      H0: r > 0

Level of significance = 5%                             N =

Johansen (Trace) stat =                                   p-value =

Conclusion:

Repeat for Rank(P) = 1

H0: r = 1                      H0: r > 1

Level of significance = 5%                             N =

Johansen (Trace) stat =                                   p-value =

Conclusion:

Johansen Max test for Rank(P) = 0

H0: r = 0                      H0: r =1

Level of significance = 5%                             N =

Johansen (max) stat =                         p-value =

Conclusion

H0: r = 1                      H0: r =2

Level of significance = 5%                             N =

Johansen (max) stat =                         p-value =

Conclusion

1. Report the summary table for Johansen tests for all five specifications

What is the best model for the data based on AIC?

1. Impulse Responses on GDP from 1sd tbill shock with the ordering as

GDP, Inflation, FX, tbill, US_tbill

What is 1 sd tbill shock?

What is the impact on GDP for 1 month =             4 month =             12 month=

GRAPH and Table

Repeat with this ordering

CAN_GDP, IPP, Inflation, US_GDP, OIL

GRAPH and Table

What is the impact on GDP for 1 month =             4 month =             12 month=

1. Forecast GDP growth for the next two years