Data Analytics-Risk Modelling Task

Risks Associated with Investing into Emerging Markets in Comparison with other Markets
Contents

Data Analytics-Risk Modelling
Introduction.................................................................................................................................................3
Motivation...................................................................................................................................................4
Hypothesis...................................................................................................................................................5
Data and Methodology................................................................................................................................6
Data.........................................................................................................................................................6
Methodology...........................................................................................................................................7
Results.........................................................................................................................................................8
Descriptive Statistics...............................................................................................................................8
Data Visualization...................................................................................................................................9
Value at Risk (VaR)..............................................................................................................................10
Conclusion.................................................................................................................................................10
References.................................................................................................................................................12
Appendix: R Code and Output Screenshots...............................................................................................14
2

Data Analytics-Risk Modelling
Introduction
Risk can be defined as the concept of taking a chance at carrying out an activity without
being certain of its success (Kiechel, 2010; Cameroon, 2013). In business terms, risk would
relate to making of financial decisions such as investing, acquiring a loan, giving out a loan and
selling stakes without being certain of the profitability of this decision (Laudon & Guercio, 2014;
Fawcett & Provost, 2013). This highlights the critical nature of risk and risk evaluation. Hence, it
is important to understand; what informs the decision to take a risk and is there a possibility of
quantifying the expected risk associated with a decision.
The modern business environment is fast paced, resulting in decisions making being
critical for any business entity. Unlike in past where the business environment allowed time for a
decision to be changed with minimal consequences, the fast pace of the modern environment has
eliminated the possibility of decision change with minimal losses. This is due to the dynamic
nature of the modern business environment. Aspects in the market place change very rapidly,
therefore a high-risk decision can quickly turn into massive losses without the possibility of
reverting the decision or mitigating losses.
Despite the nature of the modern business environment, it does not imply that risks
should not be taken by business entities (Albright & Winston, 2014; Provost & Fawcett, 2013).
Acquiring competitive advantage, new market entries, disruptive innovations and maintaining
market dominance all require exposing the business entities to a level of risk (Prescott, 2014). In
general, risk is an agent of progress in the business world. In more aggressive and competitive
markets, risk is the difference between a company going out of business or surviving (French,
2017).
3

Data Analytics-Risk Modelling
There are a number of parameters used for the quantification of the amount of risk
associated with a financial decision. Among these parameters is the quantile risk measure. The
quantile risk measure is a risk measure that evaluates the worst-case scenario associated with
decisions based on a probability of 1-α, with α referring to the percentage quantile on which the
risk measure is to be computed (Douglas, William, & Samuel, 2012; Pappas, 2016). This study is
going to consider the application of the quantile risk measure to a case study. The case study for
this research is the purchasing of stocks in the emerging markets. This study will consider the
research question; is investment into the emerging markets a high-risk investment. The research
considers that motivation underlying this study followed by definition of the hypothesis for the
study. The source of the data used for the study and the analyses processes conducted will then
be stated. Finally, the results and conclusions will be presented.
Motivation
Emerging markets refers to markets that are located in economies that are not in the
developed world (first world) (Grinin, Korotayev, & Tausch, 2016). This term is mostly used in
the share trading and stock exchange context. In this context, the markets refer to companies
either registered or operating in economies that are not in the developed world (Georgina, 2015).
Traditionally, the emerging markets have been associated with instability, which has deterred
investment into such markets (Besanko, Dranove, & Shanley, 2012). The high level of volatility
of the shares of companies in the emerging markets has in the past, been the reason why
investors hesitated to buy such shares (Heyne, Boettke, & Prychitko, 2010).
4

Data Analytics-Risk Modelling
However, over the past two decades there has been a drop in deterring factors in the
economies not in the developed world. A reduction in the internal conflicts, improvement in
leadership, increased development into the infrastructure and exploitation of resources has meant
that the shares of companies in the emerging markets has overtime become more attractive. The
above mentioned changes represent a move to a more stable economy, this stability encourages
investors by ensuring their investment will not be exposed to extreme non-market factors.
Although both market and non-market forces affect stock markets, minimum influence on stock
markets by non-market factors is preferred to encourage trading (Besanko, Dranove, & Shanley,
2012).
Despite the progresses made in the emerging economies to improve on their stability, it
still represent a risky market to invest. This is since, unlike the developed world, which has had a
long-term stability in their economies, economies that are not in the first world have only been
stable for a short period. This research aims at quantifying the amount of risk involved in the
purchasing of stocks in the emerging markets based on historical data.
Hypothesis
This study tests the hypothesis below:
Null Hypothesis (H0): The risks associated with emerging markets are high.
Alternative Hypothesis (H1): The risks associated with emerging markets are low.
5

Data Analytics-Risk Modelling
Data and Methodology
Data
The data utilized for the analysis process in this study is the edhec data set on the index
returns on investments. The data was collected from the EDHEC (EDHEC, 2019). The EDHEC
Risk Institute is an institution that is involved in conducting research in the finance industry
regarding different market and performance indices (EDHEC, 2019). The edhec data set used in
this study is continuously updated by the EDHEC-Risk Institute to include the most recent data
on the index returns on investments.
The data consist of information from the index returns on investments by hedge funds;
Hedge funds are firms that invest capital into trading based on speculations and mostly source
the capitals from funds saved in offshore accounts (Keller, 2015). Hedge funds are significant
financial institutions that offer privacy of investors when it comes to trading, with the investor
often represented by offshore companies.
The data contains information on 13 variables for a total of 275 observations. The edhec
data set is a time series data set with the observations representing monthly index returns on
investment for each of the 13 variables from 1997 through to 2019. This study is interested in the
investment into the emerging markets, and hence it utilizes the Emerging Markets variable in the
edhec data set. The Emerging Markets variable represents information on the monthly index
returns on the investment made by hedge funds into the emerging markets for the period from
1997 to 2019. This variable is numerical in nature and measured on the ratio scale.
6

Data Analytics-Risk Modelling
Methodology
Three statistical methods are applied in this research, for the analysis of the edhec data
set; descriptive statistics analysis, data visualization and inferential analysis. Descriptive
Statistics analysis is a statistical method that provides an overview of the characteristics of the
variables making up the dataset of interest (Everitt & Skrondal, 2010). The descriptive statistics
in this study provides information on the measures of central tendency and variation for the
Emerging Market variable in the edhec data set. This information will be significant in gaining a
general picture of the attributes of the Emerging Markets over the period from 1997 to 2019.
Data visualization is the tabular and (or) graphical presentation of analysis findings in a research
(Kirk, 2016). The data visualization in this study will concern producing a time series plot for the
Emerging Market variable in the edhec data set. The plot will visualize the trend in the Emerging
Markets index returns from 1997 to 2019.
The inferential analysis refers to in depth research on the characteristics of data with the
aim of understanding why the data behaves the way it does as well as drawing inferences about
the data (Barbara & Susan, 2014). In this study, the inferential analysis will involve computation
of the quantile risk measure. The Value at Risk (VaR) will be the quantile risk measure
computed in the inferential analysis in this study. Value at Risk (VaR) is a quantile risk measure
estimating the expected loss for investment assuming the market conditions are normal (Pappas,
2016). This quantile risk measure considers a given probability and time for the estimation. For
the case in this research, the Value at Risk (VaR) will estimate the expected loss in investments
made in emerging markets by hedge funds over a period of one month at 5% probability. This
loss will be computed in the form of an index value.
7

Data Analytics-Risk Modelling
The R Statistical Software will be utilized for the analysis process in this study. The
Performance Analytics package will be specifically used for the evaluation of the Value at Risk
(VaR) for the index returns on investment into the emerging markets using the VaR () function.
Results
Descriptive Statistics
The table below, Table 1: Descriptive Statistics (Measures of Central Tendency and
Measures of Variation) gives the descriptive statistics analysis results for the Emerging Markets
variable. From the table we observe that the highest index returns on investment into the
Emerging Markets by hedge funds was 0.1230, and was recorded on 30 November 2019. The
lowest index returns on investment into the Emerging Markets by hedge funds was -0.1922, and
was recorded on 31 January 1997. This indicates that since the first investment into emerging
markets by hedge funds was made in 1997, there has been an increase in returns with negative
returns in 1997 steadily turning into a positive return in 2019.
Also from the table, we observe that the average index return on investment into the
emerging markets made by hedge funds over the period between 1997 and 2019 is 0.006246.
From the standard deviation = 0.03212, we note that on average the monthly index returns on
investment into the emerging markets deviates from the average index returns by 0.03212. The
median index return on investment into the emerging markets is 0.009100.
Table 1: Descriptive Statistics (Measures of Central Tendency and Measures of Variation)
| | Index |Emerging Markets |
|:--|:------------------|:-----------------|
| |Min. :1997-01-31 |Min. :-0.192200 |
| |1st Qu.:2002-10-15 |1st Qu.:-0.009750 |
8

Data Analytics-Risk Modelling
| |Median :2008-06-30 |Median : 0.009100 |
| |Mean :2008-06-30 |Mean : 0.006246 |
| |3rd Qu.:2014-03-15 |3rd Qu.: 0.025600 |
| |Max. :2019-11-30 |Max. : 0.123000 |
| | | |
|:-------------------|:------------------|:-------------------|
|Variance |Standard Deviation |Interquartile Range |
|0.00103173278354346 |0.0321205974966759 |0.03535 |
Data Visualization
The plot in Figure 1: Emerging Markets Time Series Plot below shows the graph of the
time series data on the index returns on investment for the Emerging Markets variable. The plot
captures the trend in the returns from 1997 to 2019. From the plot, there is no linear trend in the
index returns on investments. The plot also reveals that there is no seasonality in the data, with
no visible oscillations in the curve. We however note that an additive model can be used to
provide further description of the time series since there is an almost constant size in the random
fluctuations in the data.
9

Data Analytics-Risk Modelling
Figure 1: Emerging Markets Time Series Plot
Value at Risk (VaR)
The results for the quantile risk measure are given in the table below, Table 2: Value at
Risk (VaR) analysis results. From the table we note that the Value at Risk (VaR) = -0.0522,
which represents a 5% probability of expected reduction of 0.0522 in the index returns on
investment in the emerging markets over a one month period. Comparing this with the maximum
index returns on investment into the emerging market = 0.1230 in Table 1: Descriptive Statistics
(Measures of Central Tendency and Measures of Variation) above, we note that this is a
significant reduction. For the investor expecting maximum returns, investment into the emerging
markets carry a risk of a 5% probability of a reduction of up to 142.44% in the expected returns.
With the dynamic nature of the modern business environment, 5% probability of incurring a
142.44% loss in expected returns represents a significantly high risk. Hence, we fail to reject the
null hypothesis (H0) and conclude that the risks associated with emerging markets are high.
10

Data Analytics-Risk Modelling
Table 2: Value at Risk (VaR) analysis results
Emerging Markets
VaR -0.05218143
Conclusion
The analysis in this study have revealed that there has been a steady improvement in the
index returns on investment into the emerging markets since 1997. This steady improvement is
visible from the lowest index returns being recorded in 1997 at -0.1922 and the highest index
returns being recorded in 2019 at 0.123. The results on the lowest index return being recorded in
1997, when the hedge funds began to invest into the emerging markets also indicate that the
emerging markets were initially non-performing markets with negative returns. This supports the
assumption that overtime the economies in the countries that are not in the developed world have
become more stable.
The average index returns on investment into the emerging markets is found to be equal
to 0.006246, which is a very low figure. This might be as a result of the negative index returns in
the early years of investment into the emerging markets, with the negative values weighing down
the average index returns. Hence, a calculation of more recent index returns on investment into
the emerging markets may present a different and (or) clearer picture. However, this might also
not be entirely accurate considering the fluctuations shown in the time series plot, which
suggests that value of the index returns on investment into the emerging markets fluctuates a lot.
The fluctuations in the time series plot as well point to possible high risk in investing into the
emerging markets.
11

Data Analytics-Risk Modelling
The analysis on the quantile risk measure, Value at Risk (VaR), reveal that there exist a
5% probability of a 142.44% loss in the expected returns from the investment made into the
emerging markets over a one month period. Despite the 5% probability being small, the amount
of loss in expected returns, 142.44% is notably high. This is further amplified by the low average
returns of 0.006246 in the index returns on investment, which would necessitate a significantly
large amount of investment to yield tangible returns. However, this large amount in investment
would mean the 5% probability of a 142.44% loss in the expected returns would also represent a
significantly large amount. Therefore, from the findings of the quantile risk measure, Value at
Risk (VaR), we conclude that investment into the emerging markets remain a highly risky
investment.
References
Albright, C. S., & Winston, W. L. (2014). Business Analytics: Data Analysis & Decision Making
(1st ed.). New York: Cengage Learning.
Barbara, I., & Susan, D. (2014). Introductory Statistics (1st ed.). New York: OpenStax CNX.
Besanko, D., Dranove, D., & Shanley, M. (2012). Economics of Strategy (1st ed.). New York:
John Wiley & Sons.
Cameroon, P. D. (2013). Liability for Catastrophic Risk in the Oil and Gas Industry. OGEL ,
2(2013), 5-9.
Douglas, L. A., William, M. G., & Samuel, W. A. (2012). Statistical Techniques in Business and
Economics (15th ed.). New York: McGraw Hill Irwin .
12

Data Analytics-Risk Modelling
EDHEC. (2019). Indices Investment Solutions. Retrieved from EDHEC:
https://risk.edhec.edu/indices-investment-solutions
Everitt, B. S., & Skrondal, A. (2010). Cambridge Dictionary of Statistics (4th ed.). London:
Cambridge University Press.
Fawcett, T., & Provost, F. (2013). Data Science for Business (1st ed.). London: O'Reilly Media
Inc.
French, J. (2017). Asset Pricing With Investor Sentiment: On The Use of Investor Group
Behaviour to Forecast ASEAN Markets. Research in International Business and
Finance, 5(1), 124-148.
Georgina, P. (2015). How Business Works: A Graphic Guide to Business Success (1st ed.).
London: DK Publishing.
Grinin, L., Korotayev, A., & Tausch, A. (2016). Economic Cycles, Crisis and the Global
Periphery (1st ed.). London: Springer International.
Heyne, P., Boettke, P. J., & Prychitko, D. L. (2010). The Economic Way of Thinking (1st ed.).
New York: Prentice Hall.
Keller, G. (2015). Statistics for Management and Economics, Abbreviated (2nd ed.). New York:
Cengage Learning.
Kiechel, W. (2010). The Lords of Strategy (2nd ed.). New York: Havard Business Press.
Kirk, A. (2016). Data Visualization: A Handbook for Data Driven Design (2nd ed.). Thousand
Oaks, CA: Sage Publications, Ltd.
13

Data Analytics-Risk Modelling
Laudon, K. C., & Guercio, T. C. (2014). E-commerce. Business. Technology. Society (1st ed.).
Chicago: Pearson.
Pappas, N. (2016). Marketing Strategies, Perceived Risks and Consumer Trust in Online
Behaviour. Journal of Retailing and Consumer Services, 29(1), 92-103.
Prescott, M. E. (2014). Big data and competitive advantage at Nielsen. Management Decision,
52(3), 573-601.
Provost, F., & Fawcett, T. (2013). Data science and its relationship to big data and data-driven
decision making. Big Data, 1(1), 51-59.
Appendix: R Code and Output Screenshots
14