Sunteți pe pagina 1din 11

Department of Economics

EC7091
Quantitative Methods
for
Business & Finance
MODULE INFORMATION
Academic Year:
Year:
Credits:
Semester:

2014-15
Postgraduate
15
1

Lectures:
Tutorials:
Computing Classes:
Private Study:
Total Hours

20
5
4
83.5
112.5

MODULE LECTURERS
Lecturer:
Telephone:
Office Hours:

Dr Barbara Roberts
0116 252 2906
Monday 1:00-3:00pm

Room:
Email:

Lecturer:
Telephone:
Office Hours:

Room:
Samuel Smithers
Email:
0116 252 2233
Wednesday 4:00-6:00pm

Astley Clarke 201


bbr@le.ac.uk

Astley Clarke LG07


sfts1@le.ac.uk

Main Purpose:
The module aims to develop statistical, econometric and computational skills and their application in modern
economic and financial analysis. The module consists of two distinct sections: statistics and econometrics. In the
first section, students are expected to learn the basic principles of estimation and hypothesis testing. The second
section of the module provides students with knowledge of basic econometric concepts and applied econometrics.
These include simple and multiple regression and univariate time series modelling. This module also makes use of
the computer as a tool in econometric analysis and uses one of the most widely used econometric software
packages Eviews 8.
It is essential that students practice the class exercises and past examination papers.
The course is covered in 20 hours of lectures, 5 problem classes and 4 hours of computing classes in the first
semester. Attendance at problem and computer classes is compulsory and an attendance register will be kept.
Lectures in weeks 2-4 will cover its statistics section; lectures of weeks 5-6 will cover the econometrics section.
Classes are held weekly and will start in the 3 week of the teaching semester; groups will be posted on the
postgraduate notice board. The main purpose of the classes is to apply the knowledge developed in lectures. They
will also provide students with the opportunity to discuss and clarify difficulties arising from the lectures. The
problem sheets for the tutorials will be distributed before the classes and students are expected to prepare answers
prior to the classes. Additional individual help can be given during office hours. There will be 4 scheduled hours of
computing classes, whose purpose is to tackle practical problems often encountered in (applied) econometric work.
These will occur as two 2 hour classes in weeks 5 and 6.

Learning outcomes:
Statistics section:

Knowledge of discrete and continuous probability distributions.


Knowledge of the techniques of statistical estimation and hypothesis testing
The ability to apply the above techniques to analyse economic and financial data.

Econometrics section:

The knowledge of basic econometrics.


The ability to formulate and test meaningful statistical hypotheses in econometrics.
A knowledge and understanding of the principles of regression analysis, univariate time series modeling.

Computing classes:

The acquisition of training in relevant computer software package- Eviews 8 -which will enable students to
apply the software to analyse economic and financial data. The package is available on your users.

Lectures: Tuesday 3-4pm Rattray Lecture Theatre, Wednesday 2-6pm Attenborough Lecture Theatre 1

Seminars: A timetable to follow.


Students will be allocated to classes. Please see notice boards for times, places and membership of classes.

Computing Classes: A timetable to follow.


Please see notice boards for times, places and membership of classes.

Assessment is based on a two-hour examination taken in January (80%) and a computer based project (20%).

HOW YOU WILL RECEIVE FEEDBACK THROUGHOUT THE MODULE

ewf dwr

Examination
You will receive a mark for this after the examinations have been sat. Aggregate feedback, providing a distribution of
marks in each module, will be advertised on the Departments website.

HOW THIS MODULE CONTRIBUTES TO YOUR EMPLOYABILITY

ddd

This module will identify tools that you can use to apply to data. In the spirit of the course, these tools will allow you
to be able to model and analyse financial data.

Core Reading:
Lecture notes can be downloaded from the Departmental blackboard website or will be provided as hardcopies.
Lecture notes and core reading constitute only an introduction to the subject and are not a comprehensive summary
of the material. Students are expected to undertake additional reading and study, using the supplementary reading
list and general references below as starting points and to take notes during classes.

Essential reading:
Statistics Section:

Cortinhas, C. & Black, K., 2012, Statistics for Business and Economics, John Wiley and Sons, Ltd, First European
Edition. (CB)

Econometrics Section:

Hall, S.G, & Asterios, D (2011) Applied Econometrics (2nd Edition) (HA)

Supplementary/Alternative Reading:

Statistics Section:

Lind, D., Marchal, W. & Wathen, S., 2012, Statistical Techniques in Business and Economics , McGraw Hill,
(14th or 15th edition) . (LMW)
Statistical Tables: Kmietowicz & Yannoulis, Statistical Tables for Economic, Business & Social Studies,
Longman, 2nd edition, 1988 (KY)

Note that the Kmietowicz and Yannoulis (KY) Tables are used in the examinations. Notice that there are differences
in the layout of some statistical tables in Kmietowicz and Yannoulis and in Cortinhas & Black or other textbooks.
Econometrics Section:

Brooks, C. (2008) Introductory Econometrics for Finance, Cambridge University Press. 2nd Edition or 1st
Edition (B)
Verbeek, M. (2008) A Guide to Modern Econometrics (3rd or 2nd or 1st Edition) (V)
Koop, G. (2006) Analysis of Financial Data, Wiley. (K) This book does not cover all contents of the
econometrics section, but is useful for background reading.
Wooldridge (2009) Introductory Econometrics,: A modern Approach, 4th Edition, South-Western Cengage
Learning.
Dougherty, C. (2006) Introduction to econometrics (3rd or earlier Editions),Oxford: OUP(D).
DeFusco, et al (2004) Quantitative Methods for Investment Analysis, 2nd Edition, CFA Institute.
Maddala G.S. (2001) Introduction to econometrics (3rd Edition), New York: Wiley; (M).

All students are expected to have their own non-programmable calculator which may be used in examinations.
Currently this must be a Casio FX82 or FX83. This is the only calculator permitted in University examinations.

Students should see the lecturers in classes or office hours about any academic problems concerning the course.
Personal problems affecting performance in the module should be brought to the attention of the students
personal tutor as soon after they arise as possible.

Statistics Section:
Probability and probability distributions
Review of descriptive statistics concepts. CB Chapters 2, 3. LMW Chapters 2, 3, 4. Probability
concepts. CB Chapter 4. LMW Chapter 5. Discrete and continuous random variables and
probability distributions. Binomial distribution CB Chapter 5. LMW Chapter 6. Normal
distribution. CB Chapter 6. LMW Chapter 7.
Sampling and estimation
Samples and populations. Distribution of the sample mean. Central limit theorem. CB Chapter 7.
LMW Chapter 8, 9. HA Chapter 1. Point estimates and confidence intervals. Estimation using
normal distribution and t-distribution. Confidence interval for the population mean and population
proportion. Determining sample size. CB Chapter 8. LMW Chapter 9.
Hypothesis testing
Basic steps in hypothesis testing. Type I and type II errors. Testing hypotheses about the
population mean and proportion. One and two-sided tests. CB Chapter 9. LMW Chapter 10.
Statistical inferences about two populations. CB Chapter 10. LMW Chapter 11. Non-parametric
tests. Chi-square distribution. Goodness of fit test. CB Chapter 16. LMW Chapter 17.

Econometrics section:
Simple and Multiple Regression
The Method of Ordinary Least Squares (OLS). Properties of the OLS Estimators. Hypothesis Testing.
HA. Chapter 3 and 4 B. Chapter 3

V. Chapter 2

K. Chapter 6

Autocorrelation and Heteroscedasticity


Detection and remeidies for serial correlation, multicollinearity and heteroskedasticity
HA. Chapter 5, 6 and 7 B. Chapter 4

V. Chapter 4

Univariate Time Series Modeling, Volatility and Forecasting


ARMA processes, choosing a model, stationarity and unit roots.
HA. Chapter 13, 14 and 16 B. Chapter 5 V. Sections 8.1, 8.2, 8.6-8.10

K. Chapter 9

EC7091

Mock Examination

No. of Pages:

No. of Questions:

Subject

ECONOMICS (POSTGRADUATE)

Title of Paper

EC7091 Quantitative Methods for Business and Finance

Time Allowed

TWO HOURS (2 hours)

Instructions to candidates

Answer FOUR questions


TWO questions from SECTION A and TWO from SECTION B
Equal marks are given to each question.
The approved calculator (Casio FX-83ES or FX-85ES) may be used

CONTINUED
8

SECTION A
Answer TWO questions from this section

A1. (a) You are offered an investment opportunity. Its outcomes and probabilities are
presented in the following table:
x
-$1,000
$0
+$1,000

P(x)
.40
.20
.40

Define the concept of probability distribution and explain it in the context of this
question. Calculate the mean and the standard deviation of this distribution and
interpret your results.

[50%]

(b) According to a survey reported by InsureWorld, the insurance company


FullyCovered has 40% of the insurance market for car owners. Explain the concept
of a binomial random variable and consider whether it is suitable for modelling the
number of car owners with insurance from FullyCovered.
If 10 car owners are randomly selected, how many do you expect to have insurance
with FullyCovered? What is the probability that exactly 3 are with FullyCovered?
What is the probability that more than 3 are with FullyCovered?
[50%]

A2. (a) We want to estimate the proportion of bank customers with an overdraft. In a

sample of 40 randomly selected bank customers, it turned out that 8 had an overdraft.
Explain the concept of a point estimate and a confidence interval. Calculate and
interpret a 95% and a 99% confidence interval for the proportion of bank customers
with an overdraft. Compare the two estimates and comment on the differences.
[50%]
(b) A bank manager wants to determine the amount of the average total monthly
deposit per customer at the bank. How large a sample should he take to be within

100 of the actual average with 95% confidence? He assumes that the standard
deviation of total monthly deposits for all customers is 1000. Explain your method.
[50%]
A3. (a) In the past, the mean number of days between a receipt of a complaint and
the resolution of a claim was 20 days. For the sample of 15 more recent

complaints, the average number of days between the receipt and the resolution
of a complaint was 22 days and the standard deviation was 6 days. At 5%

significance level, can it be concluded that the number of days taken to deal with
a complaint changed? Define the terms type I and type II error and explain what
they mean in the context of this question.

[50%]

(b) A company which used to control 30% of the total market share for one of its
products has launched an extensive advertising campaign. In order to investigate the
effectiveness of the campaign a random sample of 144 purchasers of this product was
contacted. It turned out that 53 purchased this companys brand of the product. Is
there any evidence that the advertising campaign worked? Outline the procedure used
in hypothesis testing and consider whether a one-sided or a two-sided test is more
appropriate here. Carry out a test at 5% significance level and explain your
conclusions.
[50%]

10

SECTION B
Answer TWO questions from this section

B1. Answer the following questions:


a) State the five assumptions made on the error term which underlie the OLS
model. (Use the mathematical notation and words) [20%]
b) Explain briefly what we mean by BLUE when we say OLS is BLUE. [20%]
c) What is heteroskedasticity? What assumption above does it violate? Briefly
explain how we try to detect it and what we can do to rectify it. [30%]
d) What is serial correlation? What assumption above does it violate? Briefly
explain how we try to detect it and what we can do to rectify it. [30%]

B2. A researcher is interested in finding out what can explain the variation in Canadian
house prices. The researcher proposed the following model:
= 0 + 1 + 2 _ + 3 _ +

The researcher is using data which was sampled from Canada in 1987 and it
contains randomly sampled data from 546 houses on the following variables:

PRICE: The sale price of the house (in Canadian dollars, $s)

BEDROOMS: Number of bedrooms the house contains

LOT_SIZE: The size of the property measured in square feet

GAS_CH: A dummy variable for heating type, 1= if house has gas central
heating; 0= Not gas central heating.

The researcher generated the following output using EViews:

11

a) Interpret the coefficients of the explanatory variables and the constant term in
the model. Does the interpretation of the constant make economic sense in this
model? [25%]
b) Conduct a hypothesis test to see if individual coefficients are statistically
different from zero. (Construct hypothesis, use the t-test and p-value). [25%]
c) Test the overall significance of the model [10%]
d) Comment on the fit of the model [10%]
e) Are there any diagnostic tests you may wish to conduct on the above model?
Clearly state the null and alternative hypothesis of these tests and discuss what
actions should be taken in the event of a rejection of the null. [30%]

B3.
a) Explain what is meant by stationarity? [15%]
b) Give a description of an autoregressive model, a moving average model and an
ARIMA model. Use notation where necessary. [25%]

12

c) The Box-Jenkins approach was a major advancement in time-series and gave us


a step by step procedure to follow to select the best fitting ARIMA model.
Describe the Box-Jenkins approach. [30%]
d) How do we test for stationarity? Describe the method of these tests in detail.
[20%]
e) What ways to do we use to make a non-stationary series, stationary before we
continue with the data analysis?[10%]

13

S-ar putea să vă placă și