Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

ECO 4185 | Financial Econometrics

Assignment 1

This assignment is due on Sunday, February 27th before midnight. You can submit this work individually or in teams of 2 or 3. You must submit only one copy per team, including a PDF file containing your results and an R file containing the code used. These two documents are necessary for your work to be considered submitted.

Exercise 1 (Asset returns) Download the adjusted closing prices for the Microsoft stock (MSFT) and the market index S&P500 (ˆGSPC) between January 1, 1990, and December 31, 2014, using the command getSymbols() of the quantmod package.

(a)  Graph the daily returns for each of the series. Make sure to adjust the axes to facilitate the comparison.

What do you notice about the volatility of the two series?

(b)  Perform the following hypothesis tests for the daily and monthly returns of each series. Use a significance

level of 5%.

i.  A test of the hypothesis that the returns are i.i.d. Gaussian using the Jarque-Bera statistic. Calculate the critical values using the quantile function of the asymptotic distribution of the test statistic under the null hypothesis.

ii.  A test of the hypothesis that the returns are i.i.d. with finite variance using the Ljung-Box statistic. Calculate the test statistic for m = 12 lags from the autocorrelation function obtained with the acf() command.

(c)  Are your results consistent with the empirical stylized facts characterizing the financial data on asset prices? Briefly comment.

Exercise 2 (Time series) Consider the following 3rd order autoregressive process with gaussian innova- tions:

rt  = 0.02 + 1.03rt − 1  - 0.42rt −2 + 0.32rt −3 + at ,        where        at  ~ N(0, 0.42 ).

(a)  Calculate the roots of the characteristic polynomial. What do these roots tell you about the autocorre-

lation function described by the process?

(b)  Calculate the unconditional mean of the process.

(c)  Simulate a series of N = 1000 observations. Note: The arima.sim() command only allows to simulate ARMA processes with zero mean.  To specify the distribution of the innovations, use the argument rand.gen  =  function(n)  rnorm(n, mean=...,  sd=...) in the previous command.

(d)  Represent on the same graph the autocorrelation function ρl  of the population (described by the model) and the autocorrelation function ρˆl  of the sample for l = 1, . . . , 50.  Add a legend to identify both functions.

(e)  Using the simulated sample, estimate the parameters of an AR(3) model and verify that the model is

adequate. Present the point estimates and their standard deviations. Are all the parameters correctly estimated? Would an AR(2) model have captured the autocorrelation of the sample?


Exercise 3 (Time series) Download the quarterly GDP price deflator series (GDPDEF) available on the FRED website using the getSymbols() command of the quantmod package. This series is commonly used to

measure inflation. The data are seasonally adjusted and equal to 100 for the year 2012.

(a)  Use the data from 1947-Q1 to 2018-Q4 to build an ARIMA model for the series and check the validity of the selected model.

(b)  Use the fitted model to predict the inflation for each quarter of 2019. Are the realized values within the

95% prediction interval?

(c)  Calculate the Mean Absolute Percentage Error (MAPE) statistic for your four predictions.

Exercise 4 (Portfolio theory) Download the adjusted closing prices of the stocks of the companies listed in the table below between January 1, 2014 and December 31, 2019 using the command getSymbols() of the quantmod package.

Symbol

Exchange

Compagny

Industry

PG

NYSE

Procter & Gamble

Consumer Goods

MMM

NYSE

3M

Conglomerate

IBM

NYSE

International Business

Machines

Tech

MRK

NYSE

Merck & Compagny

Pharmaceuticals

AXP

NYSE

American Express

Financial Services

MCD

NYSE

McDonalds

Food and Beverages

BA

NYSE

Boeing

Aerospace

KO

NYSE

Coca-Cola

Food and Beverages

CAT

NYSE

Caterpillar

Construction

DIS

NYSE

Disney

Entertainment

JPM

NYSE

JPMorgan Chase

Financial Services

JNJ

NYSE

Johnson & Johnson

Pharmaceuticals

WMT

NYSE

Walmart

Retail

HD

NYSE

Home Depot

Retail

INTC

NASDAQ

Intel

Tech

MSFT

NASDAQ

Microsoft

Tech

VZ

NYSE

Verizon

Telecom

CVX

NYSE

Chevron

Oil & Gas

CSCO

NASDAQ

Cisco

Tech

TRV

NYSE

Travelers Compagnies

Inc

Insurance

UNH

NYSE

UnitedHealth

Managed Healt Care

GS

NYSE

Goldman Sachs

Financial Services

NKE

NYSE

Nike

Apparel

V

NYSE

Visa

Financial Service

AAPL

NASDAQ

Apple

Tech