Microsoft Word – Tutorial 5 T2 2021.docx
© Copyright University of Wales 2020. All rights reserved. This copyright notice must not be removed from this
Copyright By PowCoder代写 加微信 powcoder
Copyright © Copyright University of Wales 2020. All rights reserved.
Course materials subject to Copyright
UNSW Sydney owns copyright in these materials (unless stated otherwise). The material is subject to
copyright under Australian law and overseas under international treaties. The materials are provided for
use by enrolled UNSW students. The materials, or any part, may not be copied, shared or distributed, in
print or digitally, outside the course without permission. Students may only copy a reasonable portion of
the material for personal research or study or for criticism or review. Under no circumstances may these
materials be copied or reproduced for sale or commercial purposes without prior written permission of
UNSW Sydney.
Statement on class recording
To ensure the free and open discussion of ideas, students may not record, by any means, classroom lectures,
discussion and/or activities without the advance written permission of the instructor, and any such
recording properly approved in advance can be used solely for the students own private use.
WARNING: Your failure to comply with these conditions may lead to disciplinary action, and may give rise
to a civil action or a criminal offence under the law.
THE ABOVE INFORMATION MUST NOT BE REMOVED FROM THIS MATERIAL.
© Copyright University of Wales 2020. All rights reserved. This copyright notice must not be removed from this
University of Wales
School of Economics
Financial Econometrics
Tutorial 5
1. (Error correction and common trend)
Suppose that I(1) series 𝑦! and 𝑥! are cointegrated and 𝜀! = 𝑦! − 𝛽𝑥! is an independent white
noise process. Assume that Δ𝑥! = 𝛾Δ𝑥!”# + 𝜂! where 𝜂! is also an independent white noise
process. Here 𝛽 and 𝛾 are constant parameters. Show that the changes in 𝑦! and 𝑥! are
governed by the vector error correction model
Δ𝑥! = 𝛼#(𝑦!”# − 𝛽𝑥!”#) + 𝜙##Δ𝑥!”# + 𝑢#! ,
Δ𝑦! = 𝛼$(𝑦!”# − 𝛽𝑥!”#) + 𝜙$#Δ𝑥!”# + 𝑢$! .
Express the coefficients 𝛼#, 𝛼$, 𝜙##, 𝜙$#in terms of the original parameters 𝛽 and 𝛾. Express
the shocks 𝑢#! and 𝑢$! in terms of the white noise processes 𝜀! and 𝜂!. What is the common
trend in this example and why?
2. In light of stylized facts of financial returns, how likely is that an AR(p) or MA(q) or their
combination ARMA(p,q) model are suitable for modeling financial return series? Which
stylized facts are likely to be violated?
3. (Cointegration and error correction model)
This question is based on the data in the Excel file fisher_update.XLS. The file
contains 171 quarterly observations, from 1969Q4 to 2012Q2, on the Australian Consumer
price Index (P) and on the yield to maturity of 90-day bank accepted bills (R).
(a) Generate the inflation rate as: INF=400*(log(P(1))-log(P)). When we
construct the inflation rate this way, we lose the last observation, namely, 2012Q2. We
change the sample to 1984Q1 to 2012Q1, which is the post-float period of the exchange rate.
Plot R and INF. Comment on whether or not R and INF co-move.
(b) Throughout this and the following parts of the question, continue to use the sample
1984Q1-2012Q1. Assume that both R and INF are I(1) processes. Estimate the regression
R! = 𝛽% + 𝛽#INF! + 𝜀!
and perform an ADF test, without intercept and time trend, on the residuals from the
regression. What do you conclude?
(c) Carry out the Engle-Granger cointegration test. Comment on the result.
© Copyright University of Wales 2020. All rights reserved. This copyright notice must not be removed from this
(d) Regardless of your result in (c), assume that R! and INF! are cointegrated. If the
cointegration error 𝜀! = R! − 𝛽% − 𝛽#INF! is positive at 𝑡, what would you say about the
likely movements in R!&# and INF!&#?
(e) Estimate the following two error-correction equations separately using OLS
ΔR! = 𝑐# + 𝛼#(resid01)!”# +∑ (𝜙##,(ΔR!”( + 𝜙#$,(ΔINF!”())(*# + 𝑢#! ,
ΔINF! = 𝑐$ + 𝛼$(resid01)!”# + ∑ (𝜙$#,(ΔR!”( + 𝜙$$,(ΔINF!”())(*# + 𝑢$! .
Comment on your results. Do you observe error correction mechanism in the estimated
equations?
(f) Can you reduce the “size” of the model in (e) by dropping some lags? Re-estimate the
error-correction equations when insignificant lagged terms of ΔR! and ΔINF! are dropped
from the equations you estimated in part (e). Comment on the new results.
4. Simulation Exercise in Excel.
The Analysis ToolPak is a Microsoft Office Excel add-in program that is available when you install
Microsoft Office or Excel.
To use the Analysis ToolPak in Excel, however, you need to load it first.
1. Click the Microsoft Office Button , and then click Excel Options.
2. Alternatively you may get to Excel Options from open Excel file, File -> Options
3. Click Add-Ins, and then in the Manage box, select Excel Add-ins.
4. Click Go.
5. In the Add-Ins available box, select the Analysis ToolPak check box, and then click OK.
a. Tip If Analysis ToolPak is not listed in the Add-Ins available box, click Browse to locate it.
b. If you get prompted that the Analysis ToolPak is not currently installed on your computer,
click Yes to install it.
6. After you load the Analysis ToolPak, the Data Analysis command is available in
the Analysis group on the Data tab.
Generate 2 random walk series:
𝑦! = 𝑦!”# + 𝜀!, 𝜀! ∼ 𝑖𝑖𝑑 WN N(0,1)
𝑥! = 𝑥!”# + 𝑢!, 𝑢! ∼ 𝑖𝑖𝑑 WN N(0,1)
To do this in excel first generate two standard normal random variables. Data -> Data
Analysis -> Random number generation. We need:
Number of variables 2
Number of random numbers 1000
© Copyright University of Wales 2020. All rights reserved. This copyright notice must not be removed from this
Distribution: Normal
This gives you two random normal variables. Set 𝑦# = 0, 𝑥# = 0. Generate 𝑦! , 𝑥! t>1 using
the equations above.
Regress y on x using Data -> Data Analysis -> Regression
Select range for y and x and press ok.
Analyse the output of the regression. Do you expect these results? What is going on?
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com