Research Methods
Coursework assignment
You are a researcher working for the Finance Ministry of a developing country. Your boss, the Minister of Finance has been asked to make recommendations to a government committee that has been charged with formulating a medium-term strategy for raising the country’s Gross Domestic Product (GDP) per capita over the period 2016 to 2026.
Special funding has been earmarked by the government for policy measures to support this strategy. At its previous meeting, the committee decided that this funding should be devoted to a policy measure that will produce an immediate increase the country’s rate of enrolment in secondary education. It is estimated that if this proposal is implemented, the secondary school enrolment rate (expressed as a percentage of the secondary school age population) will increase immediately by about 10%, from the current figure of 35% to an estimated 45%.
Since the previous meeting of the committee, however, the country has experienced a financial crisis. Senior representatives from the banks have been lobbying furiously for financial support to enable the banks to continue lending, in an attempt to avert a full-scale economic recession. They have argued that by providing emergency financial support now, the government can prevent the banks from shrinking their balance sheets; and maintaining a strong and vibrant banking sector is essential if the country is to achieve the targeted growth in its GDP per capita over the medium term. Emergency financial support would prevent a squeeze on bank lending which, in the absence of support, would reduce the ratio of private credit by deposit money banks and other financial institutions to GDP from the current figure of 0.3, to an estimated figure of 0.2.
You have been asked by the Minister of Finance to investigate the empirical evidence as to whether the funding would be spent more effectively on boosting secondary school education, or on bailing out the banking sector. You can recall an empirical model that addresses exactly this type of question, which was presented in a series of tutorials/workshops in which you participated during your time as a masters student at the University. You are concerned, however, that the data that were used in this exercise are out-of-date, and you have decided that it would be a good idea to update the data and re-estimate the model accordingly.
In order to complete this task, you have been assigned the following electronic resources:
1. A link to the University of Groningen Growth and Development Centre website, from which you can download ‘Penn tables’ data on the following variables:
Population (in millions)
Expenditure-side real GDP at current PPPs (in mil. 2011US$)
http://www.rug.nl/ggdc/productivity/pwt/
2. An Excel file indicators.xlsx, in which can be found data for 75 countries on the other variables to be used in the model (see below).
You intend to estimate the model using data for these 75 countries, which are listed below, under the continents/regions by which they are classified in the Penn tables:

Africa:
Benin, Botswana, Chad, Ethiopa, Ghana, Guinea-Bissau, Kenya, Lesotho, Malawi, Mauritius, Mozambique, Namibia, Seychelles, South Africa, Swaziland, Togo, Uganda, Zimbabwe
Asia:
Bahrain, Bangladesh, Bhutan, Cambodia, Georgia, Israel, Jordan, Kazakhstan, Kuwait, Laos, Malaysia, Maldives, Oman, South Korea (also known as Korea Republic), Syria, Turkey
Europe:
Albania, Bulgaria, Croatia, Cyprus, Denmark, Estonia, Finland, France, Greece, Hungary, Iceland, Ireland, Italy, Lithuania, Luxembourg, Malta, Moldova, Norway, Poland, Portugal, Slovenia, Spain, Sweden, Switzerland, United Kingdom
North America and Caribbean:
Aruba, Barbados, Belize, Dominica, Dominican Republic, Guatemala, Jamaica, Mexico, Panama, St Lucia, St Vincent and the Grenadines, United States
South America:
Argentina, Ecuador, Peru, Venezuela
The specification of the empirical model is as follows:
dlypci = ?1 + ?2lypc00i + ?3lsecedi + ?4govgdpi + ?5openi + ?6crediti + ui

where ypc00 = expenditure-side real GDP per capita at current PPPs in 2000
(US$, 2011 prices)
ypc10 = expenditure-side real GDP per capita at current PPPs in 2010
(US$, 2011 prices)
dlypc = ln(ypc10) – ln(ypc00)
lypc00 = ln(ypc00)
seced = percentage of secondary school-age population enrolled at
secondary school in 2000
lseced = ln(seced)
govgdp = share of government consumption in GDP in 2000
open = openness = share of (exports+imports) in GDP in 2000
credit = ratio of private credit by deposit money banks and other financial institutions to GDP in 2000
In 2016, your country’s data are as follows: GDP per capita (in 2011 US$) = 2450, share of (exports+imports) in GDP = 0.3, share of government consumption in GDP = 0.18, percentage of secondary school age population enrolled at secondary school = 35%, ratio of private credit by deposit money banks and other financial institutions to GDP = 0.3.
Your tasks are as follows:
1. Using the electronic resources, compile the required data for the 75 countries in an Excel spreadsheet (each row should represent a country and each column should contain the data for one variable).
2. Read the compiled data into Stata, and construct the tables of descriptive statistics that are shown below.
Table 1 Sample summary statistics for all countries

Mean Standard deviation Minimum
value Maximum
Value
dlypc
ypc00
open
govgdp
seced
credit
Table 2 Sample means by continent/region
Africa Asia Europe N America & Caribbean S America All countries
dlypc
ypc00
open
govgdp
seced
credit
Table 3 Sample correlation coefficients for all countries
dlypc ypc00 open govgdp seced credit
ypc00 - - - - -
open - - - -
govgdp - - -
seced - -
credit -
Provide a brief interpretation/commentary (a few sentences) on these summary statistics.
(Hint: For Table 2, use the Data Editor to create a new variable that codes each country according to continent/region. Then use the summarize command to generate summary statistics for countries within each continent/region).
3. Estimate the empirical model. Test the following null and alternative hypotheses using a significance level of 0.05:
(i) H0:?2=?3=?4=?5=?6=0 against H1:?j?0 for at least one j?(2...6).
(ii) H0:?2=0 against H0:?2?0.
(iii) H0:?3=0 against H0:?3 0.
(iv) H0:?6=0 against H0:?6?0.
Provide a brief interpretation/commentary (a couple of sentences each) on the results of these hypothesis tests.
4. You are aware that estimation results for any regression model are sensitive to the presence of ‘outlier’ observations. You are aware that a rule-of-thumb remedy for an outlier problem is to create a 0-1 dummy variable for any ‘outlier’ observation with a residual larger than three times the standard error of the regression. Investigate whether there are any outlier observations in the data you have used to estimate your model. If there is an outlier observation, create a 0-1 dummy variable for this observation, and re-estimate the model.
(Hint: To set up a dummy variable, use the generate command to create a new variable equal to zero on all observations, then use the Data Editor to change the required observation from 0 to 1).
5. Assume that your country’s growth in GDP per capita for the period 2016 to 2026 will be in line with the patterns suggested by your model for the period 2000 to 2010.
If the policy objective is to increase growth in GDP per capita over the period 2016 to 2026, formulate your advice to the Finance Minister on the question as to whether the special funding would be better spent on boosting enrolment in secondary education, or on bailing out the banking sector.
What is your estimated (logarithmic) rate of growth in GDP per capita for the period 2016 to 2026 if your policy recommendation is accepted?
(Hint: Compare the fitted values of the dependent variable obtained by substituting the values of the covariates into the fitted regression equation: firstly, if the special funding is used to boost enrolment in secondary education and the banking sector is permitted to reduce lending; and secondly, if the special funding is used instead to prevent any reduction in lending, and there is no boost to enrolment in secondary education).
Instructions for submission
You are required to submit a concise written report (electronically via Turnitin, and one hard copy). Marks will be awarded for accuracy in the construction of the data set and in the conduct of the estimations and hypothesis tests, and for careful presentation of estimation and hypothesis test results using a format similar to what you will find in textbooks or journal articles. Stata output may be submitted as an appendix. Marks will be lost if you submit Stata output only, without bothering to write up the results in a suitable format. You are not required to submit your data, either in Excel or in Stata format. If you wish, you may work together with other students; but your final written submission must be prepared individually, and must be your own work.
Submission deadline: Monday 20th December 2016