讲解cross-sessional、辅导Java/c++、讲解WRDS留学生、CS/python讲解

Coursework for those who only attend week 4&5 session

You are required to work on this individual project on your own, to gain hands-on experience in

dealing with financial data from security markets. This coursework comprises two parts. The first

task focuses on the time series analysis and the second task emphasizes on the cross-sessional

analysis.

Obtain three stocks and one stock market index from Shanghai Stock Exchange, and three stocks

and one stock market index from Shenzhen Stock Exchange.

I. Obtain the end of month data of your chosen stock and market index over the sample period

from January 2008 to December 2017 in SAS studio from WRDS. Compute the monthly

returns of these stocks and indexes.

(10 marks)

II. Plot each stock returns against two stock market indexes. Describe the salient features of them.

(10 marks)

III. Generate a summary statistics table of these stocks and indexes returns, including the 5th

percentile, 25th percentile, mean, median, 75th percentile, 95th percentile, standard deviation,

skewness and kurtosis. (14 marks)

IV. Test for stationarity of the return series by using the Dickey-Fuller (DF) test. Specify the model

of the test and discuss the results. (14 marks)

V. Compute and discuss the pair-wise correlations between these return series. (10 marks)

VI. For each stock i (i=1,…,6), run the following regression:

Eq (1)

where, is the return of stock i on month t, and rm,t is the return of one of the market

index on month t. Summarize and discuss your regression results. (14 marks)

VII. For each stock i (i=1,…,6), run the following regression:

Eq ( 1 )

where, is the return of stock i on month t, and rm1,t is the return of the market index

from Shanghai stock exchange and rm2,t from Shenzhen stock exchange on month t. Discuss

your regression results in comparison with findings from the Section VI. (14 marks)

VIII. For each market index, run an AR(1) model. Estimate the autocorrelations up to 12 lags of

it mt it , ,, r r =+ + ab e

i t, r

it m t m t it , 1 1, 2 2, , r rr =+ + + ab b e

i t, r

the data series together with their t-statistics. Describe the proceeding procedures to choose

the appropriate model specification and to determine the number of lags to be included.

Justify the choice you made about the specification and number of lags to model the data

series in this section. (14 marks)

Further information on the assignment will not be provided. Each person should undertake

their own research and make decisions on the approach to present and discuss the

information required and the assumptions used. The module material (lectures, tutorials

and textbooks) can provide a good basis to build upon but higher marks will be awarded

for analysis that goes beyond these material. Please provide reference on all additional

sources of information used (in the selection/discussion of assumptions used as well as the

general analysis). The assignment should be structured as follows:

All calculations for all questions as well as raw data must be presented in your SAS

code that submitted to me. In order to be awarded with the full mark for each

question the spreadsheet must include all information and all correct calculations; it

must also be well-presented, clear and user-friendly. Reasonable comments should

be included in your code.

YOUR COMPLETED ASSIGNMENT MUST BE SUBMITTED NO LATER THAN 5:00p.m.

Friday 21thDecember 2018 by email to the module leader.

PLAGIARISM and COLLUSION

All sources should be acknowledged in the text based on the Harvard referencing

system. Individuals suspected of plagiarism, either of published work or work from

unpublished sources, including the work of other students/groups, or of collusion will be

dealt with according to University guidelines. You will are also required to submit an

electronic copy of your assignment which will be put through the plagiarism detection

service