Page 22 - Azerbaijan State University of Economics

THE JOURNAL OF ECONOMIC SCIENCES: THEORY AND PRACTICE, V.72, # 2, 2015, pp. 4-23

Mineral and Quarrying Goods 3.96 -0.54** 0.29 1,0
Note: F-stat is the F-statistic for the bounds-test of cointegration. ECT is the error correction
term. R-squared is the coefficient of determination from the error correction regression. Lag
order is the optimal lag length according to the Schwarz-Bayesian criterion. *,**- indicate
statistical significance at the 5% and 1% level, respectively.
Table 7: ARDL Regression Estimates

Factors Estimate Constant D(EXR)
All Industries 2.18 -3.58 -1.23
Non-Heavy Industries -0.30 0.87 -0.17
Communication and Utilities -3.19 6.46 0.55
Textiles and Light Equipment -0.77 1.59 -0.46
Machinery, Vehicles, and Related Tools -0.17 0.28 -0.30
Heavy Metals and Inorganic Chemicals 0.13 0.43 -3.96
Storage and Infrastructure 0.34 -0.68 1.14
Agriculture and Organic Chemicals 0.44 -0.77 -0.25
Mineral and Quarrying Goods -0.59 1.15 -0.32
Note: Dependent variable is factor-specific trade balances. Independent variable is the ln-
transformed US/YUAN bilateral exchange rate. Estimates in column 2 refer to the long-run
elasticity of the factorial balance of trade parameters in response to a 1% shock in the exchange
rate. D(EXR) is the lagged exchange rate variable indicating the short-run dynamics.

Figure 1: CUSUM Test for Heavy Metals and Inorganic Chemicals

22