ECON339 Applied Financial Modeling
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
ECON339
Applied Financial Modeling
Wollongong
Mock Final Examination Paper
Spring, 2021
Q1. The Australian dollar is regarded as a commodity currency. Assuming that demand for iron ore is not affected by changes in commodity prices, this implies that an increase in the commodity price drives the external value of the Australian dollar. Panel 1A is a plot of the commodity price index (CP) that captures the iron ore price. Panel 1B is a plot of the external value of AUD expressed in terms of the Chinese Yuan (EXRATE) for the period Feb 2010 to Aug 2021.
Panel 1A Panel 1B
160 140 120 100 80 60 40 10 11 12 13 14 15 16 17 18 19 20 21 |
7.5 7.0 6.5 6.0 5.5 5.0 4.5 4.0 10 11 12 13 14 15 16 17 18 19 20 21 |
(a) Briefly explain the movement of the CP and EXRATE. [2]
(b) Panel 1C and 1D show the Augmented Dickey-Fuller (ADF) test results for the log(exrate) (i.e., LEXRATE) and the log(CP) (i.e., LCP). Why is the ADF test preferred to the DF test? [2]
(c) Write down the unit root test regression specification. [2]
Panel 1C (LEXRATE) Panel 1D (LCP)
Exogenous: Constant, Linear Trend Lag Length: 0 (Automatic - based on SIC, maxlag=13)
t-Statistic Prob.*
Augmented Dickey-Fuller test statistic -2.422430 0.3664 1% level 5% level 10% level
|
Exogenous: Constant, Linear Trend Lag Length: 1 (Automatic - based on SIC, maxlag=13)
t-Statistic Prob.*
Augmented Dickey-Fuller test statistic -1.613724 0.7827 1% level 5% level 10% level
|
(d) Interpret the unit root test results in Panels 1(c) and 1(d). What can you infer about the stationarity property of LCP and LEXRATE? [2]
Q2. Suppose you are interested in the short-run dynamic of commodity price changes and changes in the Australian dollar from Feb 2010 to Aug 2021.
(a) Why do you believe it is appropriate to use a Vector Autoregression model to study the short-run dynamic? [2]
(b) The table below shows the different criteria used to determine the appropriate lag length of the VAR model. What is the optimal lag length? [2]
VAR Lag Order Selection Criteria
Endogenous variables: DEXRATE DCP
Exogenous variables: C
Date: 09/26/21 Time: 19:07
Sample: 2010M02 2021M08
Included observations: 130
Lag LogL LR FPE AIC SC HQ
0
1
2
3
4
5
6
7
8
544.0680 564.6249 569.0219 569.8486 571.1397 575.7100 578.3977 579.1319 580.6602
NA 40.16489* 8.455761 1.564410 2.403519 8.367180 4.837851 1.298896 2.656903
8.19e-07 6.35e-07 6.31e-07* 6.63e-07 6.91e-07 6.85e-07 7.00e-07 7.36e-07 7.65e-07
-8.339508 -8.594229 -8.600336* -8.551517 -8.509842 -8.518616 -8.498427 -8.448183 -8.410157
-8.295392 -8.461881* -8.379757 -8.242705 -8.112799 -8.033341 -7.924920 -7.786444 -7.660186
-8.321583
-8.540452*
-8.510708
-8.426036
-8.348510
-8.321433
-8.265392
-8.179297
-8.105419
* indicates lag order selected by the criterion
LR: sequential modified LR test statistic (each test at 5% level)
FPE: Final prediction error
AIC: Akaike information criterion
SC: Schwarz information criterion
HQ: Hannan-Quinn information criterion
Q3. Consider the following simultaneous equation models.
1௧ = ⃞ + ଷ3௧ + ⃞1௧ + 1௧ 2௧ = ଶ + ⃞1௧ + ଷ3௧ + 2௧
3௧ = ଷ + ଶ2௧ + ଶ2௧ + 3௧
(1)
(2)
(3)
(a) Can you estimate equation (1) with OLS assuming 1 and 2 are exogenous? Explain [2]
(b) Use the order condition to identify which of the above equations are just identified. [2]
2021-12-05