Time Series Analysis – Forecasting Currency

Time Series Analysis – Forecasting Currency
he purpose of this study is to see if it is possible to predict future exchange rate movements through the use of time-series models. This study will use univariate
models, including the autoregressive integrated moving average (ARIMA) model, and the autoregressive moving average (ARMA) model. These two models will be applied to
two currency pairs: the United States Dollar (USD) / Japanese Yen (JPY), and the USD / Euro (EUR). Both pairs will be based on daily closing rates over a 10 year
period: January 1, 2005 to January 1, 2015. These models will be compared to determine which model most accurately matches the empirical evidence. * Must use STATA for
data analysis. Instructions from professor: Select and investigate the behaviour of some relevant time series variable/s in Economics making use of some of the time
series models learned during the course. For example, you may choose a topic for your project in applied macroeconomics (e.g. exchange rates, interest rates,
inflation, GDP) or empirical finance (e.g. stocks, shares, commodities). Once you define your topic of interest, develop a
model that will allow you to forecast their likely future trends. Critically evaluate your model using the techniques learned during ECO402 and discuss potential
improvements and extensions.1) Must be done with STATA. All regression output from STATA should be included in the appendix. You may include Figures and Tables within
the main body of the report but tables may not be just copy and paste from the output of the software. 3. Final reportData may be obtained, among a large number of
available sources, from:
a) Datastream, available to all Masters students in the Business School Financial Labb) CEIC, CSMAR or other databasec) FRED, available at:
http://research.stlouisfed.org/fred2/d) QUANDL, available at: https://www.quandl.com/
It is part of the assessment to ensure that the group acquires the appropriate data to be analysed. You
need to explain the behaviour of the variable of interest in some detail. You would also like to look at
other factors that might explain variation in your series.As a friendly suggestion, a project may contain:? Literature review.
? Description of sources and data of the project.
? Basic / univariate model: specification, selection process and results from estimating the
selected models
? Advanced / Multivariate model: specification, selection process and results from estimating the
selected models
? Discussion of the models
? Prediction / forecast and performance
? Evaluation
? Conclusions
? References
You may merge together some of them or have additional sections if necessary (e.g.: Introduction,
appendix, etc).*** I already wrote a Lit. Review that was submitted to the professor, including 5 references. I will submit this to you in a separate order for a
rewrite, as submitting it was just to show progress. I will submit it to you so you can rewrite it to match your style of writing.* That added to the rest of the
report will add to over 3000 words. So I will order 2700 words on this and later i will add that after the rewrite. **** We are just average students in a time-series
class in a masters of finance course. If the final product is too high level he may question us. I don’t know how possible it is to write at certain levels, but if
it’s possible to write a product that would get between a 3.0-3.5 gpa level in a normal finance program course, that would be great. Something that would get a 4.0 at
U of Chicago might draw too much attention. I don’t want to sound too demanding. Just something to keep in mind if possible.

FOR YOUR ASSIGNMENTS TO BE DONE AT A CHEAPER PRICE PLACE THIS ORDER OR A SIMILAR ORDER WITH US NOW