Master of Science in Financial Mathematics

Permanent URI for this collectionhttp://192.248.9.226/handle/123/67

Browse

Now showing 1 - 20 of 71

item: Thesis-Full-text
Age structural transitions and inflation dynamics in selected south Asian countries
(2020) Ariyarathna PAHR; Sivathas K; Dissanayake R
The aim of this study is to find out whether there is significant effect from age structural transitions on inflation dynamics in some selected South Asian countries such as Sri Lanka, India and Bangladesh. It has been shown that the age structural transitions can disrupt macroeconomic equilibriums of countries, if unattended. Sri Lanka is facing a decreasing youth dependency ratio growth and increasing elderly dependency ratio growth phase as a result of age structural transitions. This poses serious concerns in terms of obvious factors such as health budget and social security payments to elders in future. In this thesis, I endeavor to study whether age structural transition has an implication on an important macroeconomic indicator which is inflation. A structural VAR model has been constructed to answer this issue. Elderly dependency ratio growth, youth dependency ratio growth, real interest rate and output gap growth are the selected variables from 2003 to 2018 for these models. Cholesky decomposition and structural decomposition used to check the robustness of the models. The empirical results showed that the growth of youth dependency ratio is inflationary for Sri Lanka. But for India and Bangladesh growth of youth dependency ratio does not have any significant effect on inflation. Growth of elderly dependency ratio does not have any significant effect on inflation for Sri Lanka, India and Bangladesh. But the magnitude of the impact from elderly and youth dependency ratio growth on inflation is around 5% over the period of 10 months as the variance decomposition reveals for Sri Lanka and for India and Bangladesh it is around 2%.
item: Thesis-Full-text
Analysing the significant factors which are affected to the selection of higher education opportunities in the private institutions
Waidyasekara, VT; Cooray, TMJA
Gaining higher education is vital for a person to find more lucrative careers pursuing a better professional and personal life growth. In the modern world today, private education institutes play an imperative and a competitive role by opening up many more opportunities for those who are seeking higher education aspirations. At such a turning point of a life, the determinants considered by the students when selecting higher education opportunities in the private institutions are worth to study. The study was carried out with the objectives of identifying the potential students for a particular programme of a private higher education institute in Sri Lanka and to identifying the salient factors which are considered by the students when selecting higher education opportunities in the private institutions. Due to the unavailability of the secondary data source, primary data was collected through a questionnaire survey and descriptive analysis has been carried out to check the relationship between the response variables and other explanatory variables. Due to the availability of colliniarity between explanatory variables and as those variables, factor analysis has been carried out. Hypothesis testing has been carried out for ordinal data using Kruskal Wallis test. As per the major findings, higher studies are more preferred by male students those who have done mathematics for their Advanced Level studies. The main sources, referred for gathering course information are friends and the websites. With reference to the education background and occupation of the respondents’ parents, the most have advanced level qualification, most fathers are government servants and businessmen and mothers are house wives. Parents are the main source of financial contributor for the higher studies of their children. Majority of the respondents live and have studied at Colombo and have gone to national schools. According to the factor analysis, Study Programme, Influence, Accommodation and Attitudes are the determinants considered by students those who are pursuing higher education. According to the Kruskal Wallis test Study Programme depends on gender, programme type (Degree, Advanced Diploma, Diploma, and Certificate) and programme area (Engineering, Medicine, Physical Science, Bio Science, Management and Arts). The Influence depends on programme type and programme area. Accommodation depends on gender, programme type, programme area and type of school. Attitudes depend on programme type, programme area, education of the mothers, district of the school and type of the school.
item: Thesis-Full-text
Analysis of internal factors affecting share prices:
(2020) Umathevan B; Karunarathna KANK
The stock market plays an important role in economic progress of any nation and share price is a key aspect in stock market. Share price is the value of single share of a company's multiple sellable stocks. It represents not only present value of a company, but also the growth. However, the stock market is dependent on several factors and hence, it fluctuates and predicting becomes much more complicated. This study aimed to determine internal factors that influence share price of 24 diversified financial companies listed in Colombo Stock Exchange in the period from 2014 to 2019. Impacts of six variables namely return on assets, return on equity, book value per share, earnings per share, dividend per share and dividend yield on market price of shares in the respective sector were studied. Yeo and Johnson power transformation was used to transform the data and then used for model fitting. The panel data models: ordinary least square with common effect model; fixed effects model; and random effects model were tested. Among these models, the best model was fixed effects model. The results indicated that return on assets, return on equity, book value per share, earnings per share and dividend per share have positive relationship with share price and dividend yield has negative relationship with share price. Further, all these factors have significant impact on market price of share and dividend yield has higher influence whereas book value per share has lower influence on share price. Results of this study implies that investors can take most advantageous investment decisions and be guaranteed favorable returns if they take into consideration of these significant determinants In the future, it can be aimed to complement a study in various sectors with in internal and external variables of and a large timeframe. This would provide better insights on the determinants of share price
item: Thesis-Full-text
Analysis of the relationship of stock market with exchange rate and spot gold price in Sri Lanka
Wickramasinghe, WTN; Dissanayake, R
Intention of this thesis is to analyze the interrelationship of stock market volatility with LKR/USD exchange rate and spot gold prices in Sri Lankan stock market. There are several statistical techniques used in this study, such as Unit Root Augmented Dickey Fuller test, Box-Pierce test, Ljung–Box test, ARCH LM test in order to identify the relationship between stock returns and macroeconomic variables. Daily data for All Share Price Index, Exchange rate and Spot gold prices were collected over six-year period from 4th Jan 2010 to 4th Mar 2016. EGARCH specification, which was proposed by Nelson was used to model the variables in order to derive an equation to forecast the future behavior of stock returns. Evidently, statistical model depicted a strong evidence on non-existence of relationship between stock returns and exchange rate but it was proven the strong negative relationship between stock returns and spot gold price returns.
item: Thesis-Abstract
An Analysis on deterministic chaos of exchange rates during COVID -19 outbreak
(2023) Thathsarani, AA; Ganegoda, NC
The COVID-19 influence has had a significant impact in a number of areas, including the economies of many nations. Exchange rates also show noticeable fluctuations during the pandemic period, hence analysis of the behaviour of these fluctuations is useful to make better decisions. This study aims to analyze the deterministic chaos of exchange rates during the COVID-19 period in 2020, using Poincare's definition and forecasting with ARIMA and ETS models, using R software. From 1'1 January 2016 to 3181 December 2020, daily rates between the US Dollar, Euro, British Pound, and Japanese Yen and the Sri Lankan Rupee were collected from reports of the Central Bank of Sri Lanka. Data from January 2016 to February 2020 are considered for model fitting and the forecast period is considered from March 2020 to December 2020, considering the COVID-19 first wave and the beginning of the second wave in Sri Lanka. According to Poincare's definition, the properties of deterministic chaos are depicted by all four rates, hence showing deterministic chaos during the considered COVID-19 period. Forecasts using ARlMA and ETS models also determine that the USD, GBP, and Japanese Yen show clear chaotic behaviour, while Euro rates show slight chaotic behaviour at the beginning of the COVID-19 outbreak in Sri Lanka.
item: Thesis-Abstract
An analysis on monetary aggregate that reflects macroeconomic framework of sri lanka
Perers, RNS; Abeysekera, N
This thesis investigates the monetary aggregate that reflects the macroeconomic condition of Sri Lanka, the long run money demand relationship, and the determinants of money demand in Sri Lanka since 1978. The estimation ofmoney demand functions for narrow money (Ml) and broad money (M2) using quarterly data for 1978 Quarter 1 to 2009 Quarter 4 forms the basis ofthis investigation. Econometric techniques such as unit root tests, Vector autoregression (VAR) models, Cointegration relationships and some economic fundamentals like elasticities were used to achieve the objectives ofthis study. Set ofVAR models are formed and they suggest that M2 growth is best explained by the macro economic variables; Gross Domestic Product (GDP) growth, Colombo Consumer Price Index (CCPI) growth, Real Exchange rate index (REX) growth, and growths of savings and fixed deposit rates ofNational Savings Bank (NSB). This finding is further strengthened by the results of cointegration analysis as only M2 is cointegrated with its determinants. M2 growth is forecasted, to assist policy makers to have a control of monetary expansion. Only M2 had meaningful cointegrating relationships with its determinants ofGDP, CCPI, REX, and One year Fixed deposit rates of National Savings Bank and Commercial Banks. This indicates that M2 demand is stable while Ml demand is not. Therefore, in formulating monetary policy in Sri Lanka, M2 is the aggregate that need to be considered as it better reflects the macroeconomic condition. Results also suggest that, there exist high Income and Price elasticities where as low elasticities for interest rates.
item: Thesis-Abstract
Analyzing & predicting the impact of news on the ASI return of Colombo stock exchange through black-litterman model
(2022) Perera PRSG; Ranasinghe L
Considering the historical data, we can conclude that news on attacks, international political problems, natural disasters, and protests have a negative impact on the stock market return while changes in Government Acts and Election period have a positive impact on stock market return. Further, Monetary & Fiscal policy changes and news on major investments have a neutral impact on the return. The significance of the news has been tested using the t-distribution method. It concludes that Monetary & Fiscal policy changes and news on major investments don't have a significant impact on index returns while other selected events have a significant impact on the index returns. By applying the Black-Litterman model together with hypothetical views, one can develop a P matrix to derive/ predict the return of the index movement. Therefore, an investor/analyst can consider the significance level of the news items (t-distribution results) and the type of impact (negative/positive) when assigning numbers and views for the P matrix.
item: Thesis-Abstract
Analyzing the profitability of option trading in Sri Lanka
(2015-02-22) Jayawardena, AS; Jayasekara, V
The aim of the research was to identify the introduction of options to CSE will give the investors the opportunity to gain more profit. The research was based on equity and index European call options and focused on two objectives. The first objective was to identify if equity options have an advantage over direct investment in the underlying stock in terms of returns. The second objective was to compare the returns of equity options with the return of index options Three basic strategies were used to analyze the potential returns from options in order to compare with the stock investment returns from a fixed investment amount of 1 million. First strategy was to invest in the same number of options as an alternative to investing directly in stocks and invest the cash remaining at risk free rate. It was concluded that this strategy is recommended only as an alternative for investors’ having intentions on buying the stock at a fixed price. Both equity options and index options did not provide better returns. The only advantage observed in terms of better returns was investing in put options in a bearish market. Second strategy was to use the entire investment amount to buy options. It was concluded that this was a strategy recommended for investors willing to take very high risk by continuously investing in options in order to benefit from the highest percentage of profit observed out of all 3 strategies. The index options showed a clear advantage over equity options in terms of returns and risk. Third strategy was to use the frequently employed 90-10 strategy used by investors in options trading where 10% of the investment money is used to buy options and 90% cash remaining from the options investment is invested at risk free rate. This strategy showed better returns than strategy 1 but lower returns than strategy 2 but did not always give better returns than direct stock investments. It was concluded that this strategy is recommended for investors who desire returns without having the intention to own stocks but need to limit the risk taken. Overall it was concluded that introducing equity and index options has its advantages for investors.
item: Thesis-Abstract
Applicability of geometric brownian motion and geometric fractional brownian motion to forecast share prices of telecommunication services sector in Sri Lanka
(2022) Athukorala AKKK; Dissanayake R
The Brownian motion is a Mathematical concept which European botanist Robert Brown introduced in 1827 to study the behaviour of molecules. The Brownian motion concept was transformed into many versions, and Geometric Brownian Motion (GBM) and Geometric Fractional Brownian Motion (GFBM) is the latest transformation of this concept. The GBM and GFBM are mathematical models used to forecast prices of stocks, commodities, etc. In this study, the GBM and GFBM were tested to estimate the share prices of telecommunication industry companies in Sri Lanka. The two sample companies were selected by representing 18% of the population of the telecommunication industry group. The five-year share prices were collected from sample companies: Sri Lanka Telecom PLC and Dialog Axiata PLC. The two models were implemented by estimating parameters such as the drift, the volatility, probability measurement and the time interval. In addition, the Hurst component was generated by a MATLAB program for GFBM. This study is concluded that GBM is the most accurate model for forecasting share prices of the telecommunication industry group with minimum mean absolute percentage error (MAPE).
item: Thesis-Full-text
Application of game theory on financial benefits and employee satisfaction :
(2020) Jayasekara DDGT; Wijayanayake AN
In any business organization, there are two parties inside. The company and the employees, the company always tries to maximize their profit as well as employees try to demand their gains or benefits. This is not a linear relationship, because the profit and employee earnings have disproportionate equilibrium. To maximize the profit the management always focuses on the performance of the employees and to reduce the cost. As per the motivational theories, it is clearly indicated that the employees have different types of needs. Therefore, the management should focus on a wide range of factors to satisfy the employees to absorb the maximum strength they are holding. In this research, we focus on both employees and the management of a state bank. Management of the state bank is always eager to minimize the cost and maximize the profit. However, the employees make every endeavor to elevate their earnings, which will be a cost to the company. The conflict begins at this point. The author observed that the problem of the institutions and introduced the Game Theory which provides a mathematical framework for understanding the optimal outcome and what the tradeoffs are to achieve that outcome. Therefore, it has to found the main financial benefits and their effectiveness on employee satisfaction to maximize the profit. To fulfill that objective it has to be observed the benefits given to employees, the effectiveness of those benefits on employees and finally recommend an effective benefits allocation mix to the organization, which will address both employee and the top management. In this game, the top management can be denoted as player and there is using Maximin strategy to maximize their profit. The employees play the game as opponent and they always try to use Minimax strategy to minimize their maximum lost. This is a cooperative game consisting of two parties, which are presenting various strategies to overcome their common issues. Therefore, this game consists of mixed strategies. Management introduced various benefits. The employees’ perspective, their answers are varying according to their needs. Therefore, the accuracy and reliability depend accordingly on the selection of the sample units. The sampling technique is uniquely done by considering various parameters. During the data analysis, it is proven that this game is not having any pure solution. The results are based on the probabilities after using the values in linear programing techniques. According to the results the most suitable allowance is medical allowance to allocate more funds because the probability of that is 0.96. According to the test results, it is clearly state that there are some benefits which are totally useless to provide such as Key Holding, Disturbance and Cash loading and there are some benefits that the management should allocate more to motivate the employees as well as to gain profit.
item: Thesis-Abstract
An Approach to investigate the relationship between share prices and macroeconomic variables
(2014-12-12) Jayasundara, AN; Cooray, TMJA
With the development of the economy in Sri Lanka and low interest rate for savings influencing people to invest their money in other profitable areas. Therefore stock market is one of the good opportunities that can open the door for local investors as well as foreign investors to invest their money. This study examines the causal long run relationships among stock prices and macroeconomic variables and forecasting stock prices in an emerging stock market, the Colombo Stock Exchange (CSE). Data is used on four macroeconomic variables obtained by web site of Central Bank of Sri Lanka and the All Share Price Index (ASI) of the CSE obtained from Data Library CD published by the Colombo Stock Exchange for the period January 2003 to December, 2010. Johansen’s co-integration test, Granger Causality Test and econometrics techniques with regression analysis were used in the empirical analysis and indicate that there are long-run causal relationships among stock prices and macroeconomic variables where as Money Supply (M1) and Interest rate in Sri Lanka. These results indicate that stock prices can be predicted from certain macroeconomic variables. The above results have implications for investors, both domestic and international.
item: Thesis-Abstract
Assessing the predictability of all share price index of Colombo stock exchange using different models : a case study during the COVID - 19 pandemic
(2023) Jayakody, G; Jayasinghe, JABU
The aim of this investigation was to assess the predictability of three models: Autoregressive Integrated Moving Average (ARIMA), Seasonal Auto-regressive Integrated Moving Average (SARIMA), and Dynamic Harmonic Regression (DHR) model, both prior to and following the Covid-19 outbreak. Every model was crafted with great care and then compared to determine the optimal method for predicting future outcomes. The findings suggested that, during the Covid-19 period, the DHR model outperformed the other models as it had the lowest Corrected Akaike’s Information Criterion (AIC) value. According to the Portmanteau test, the residuals were random and not correlated, indicating that all the models were adequate for making predictions. Although the rapid decline of CSE was captured by both the ARIMA and DHR models, the DHR model yielded more significant results. In contrast, prior to the pandemic, the ARIMA model performed well and effectively captured the underlying trend compared to other models. However, forecast errors indicated that DHR model was more appropriate for predicting daily share indices with long intricate seasonal variations compared to the SARIMA model. As a consequence, stakeholders were able to make accurate investment decisions even in the midst of the outbreak. Finally, the Engle’s ARCH test was conducted to analyze the occurrence of volatility clusters during the pandemic, and it was identified that there were notable fluctuations in volatility throughout the pandemic period.
item: Thesis-Full-text
The Behavior of sector return and volatility around budget : evidence from Colombo stock market
Bhashani, KLS; Dissanayake, R
The study examines the behavior of stock returns and volatility in Diversified Holdings (DIV) sector of CSE around three annual government budget announcements. The daily returns of the sector over a period of three years from 1st April 2015 to 29th March 2018 are tested using three types of conditional time varying models, namely GARCH, EGARCH and GJR-GARCH. Three cases are considered using the dummy variable for =5, 10 and 15 with three scenarios, number of days on pre- budget, pre and post budget, post- budget for each case. Seven models are fitted except pre-budget with n=10 and pre-budget with n=15. This study finds strong evidence for the presence of budget announcement effect in stock returns and volatility of the sector. Returns during all considered windows are significantly negative and it implies that significant reduction in return. This reduction is increasing when getting closer to the budget date. Due to this effect investors can earn an abnormal return by buying stocks before five days of the budget announcement or after five days of the budget announcement and selling stocks after 15 days from the budget date.
item: Thesis-Full-text
Casual relationship between construction activities & GDP growth in Sri Lanka
(2015-08-26) Athukorala, R; Cooray, TMJA
The construction industry plays a vital role in the socio economic development and national fiscals in any country. Usually it provides a considerable share towards the Gross Domestic Product (GDP) and Gross National Product (GNP) of the economy. Further it helps to bring lot of development goals for any country such as providing infrastructure, technology, machinery, engineering services and employment opportunities. Construction industry is a highly booming sub sector in Sri Lankan economy. The sector alone has contributed 6.6% in 2009 to 8.7% in 2013 towards the overall GDP. Therefore it has indicted a significant impact to the economy of the country. This study helps to understand mathematical relationships between construction industry and economy in an investor perspective and economic policy development standpoint. Also it helps to evaluate the structures of government policies, their effectiveness as well as direct and indirect impact of social wellbeing in the country. This study focuses on the causality relationship between the developments of construction activities and the GDP Growth in Sri Lanka. It describes as a country how construction activities have been responded to the trend of national economy and vice versa. Empirical data of economic indicators and construction index were used to determine the Granger Causality Test for the period of 1990 to 2013. Therefore, it checked the associations between national economic statistics and construction activates in Sri Lanka specially to identify unidirectional and bidirectional relationships among the variables as well as short term and long term relationships. The research reveals the Balance of Trade (BOT) has a relationship between previous year Gross Domestic Products (GDP) and a year before. Also it reveals that All Construction Cost Index (ACINDEX) has an impact on last three year GDP figures, Construction sector Gross Domestic Product (CGDP) figures and BOT. Therefore it can confirm a strong relationship between construction activities and economic growth in Sri Lanka.
item: Thesis-Abstract
CEnhanced camshift kalman filter for object tracking
(2015-11-27) Fernando, WSP; Cooray, TMJA
In this thesis an enhanced Cam-shift Kalman object tracking algorithm for video surveillance and object tracking was developed. And this new algorithm was based on a modified Cam-shift tracking algorithm and the Kalman filter. This modified Cam-Shift algorithm solves a major drawback in the classical Cam-Shift algorithm such that the search area for the next frame was optimized, so that the time taken to track the object was minimized. The classical Cam-Shift algorithm for tracking performs well under perfectly maintained conditions such as light condition and without partial occlusions that constitute a good tracking method. However, under different environment conditions and with occlusions the algorithm fails. To test the performance of the enhanced Cam-Shift algorithm color of the object was selected as the feature for identifying the object, and was compared with the performance of the classical Cam-Shift algorithm. Also mean-shift algorithm was also incorporated for the comparison. In order to enhance the performance and accuracy under cluttered environment, the presence of noise and occlusions Kalman filter was combined. When the object disappears from the scene partially or fully the algorithm is capable of tracking the object. The experimental results verifies the ability of the enhanced Cam-shift Kalman object tracking algorithm in comparison to the classical Cam-Shift, which can locate the target object more effectively.
item: Thesis-Abstract
A Clustering based approach to study the impact of COVID - 19 pandemic on Colombo stock exchange
(2023) Saumyamala, MGA; Dharmarathna, HAS
Investor’s main objective is to maximize the portfolio returns while minimizing the risk. Unsystematic risk inherent to the industry can be minimized by diversification and systematic risk is hard to avoid. Main reason for the systematic risk is economic recession and covid pandemic is the most recent recession affected Sri Lankan economy. The primary objective of this research is to study the impact of covid-19 pandemic on risk and return of all listed companies in Colombo stock exchange (CSE) using clustering-based approach. For this study stock market data for 3-year period from 1st January 2019 to 31st December 2021 were used. The first dataset of All share price index (ASPI) which represent the behavior of all the listed companies was used to identify the different periods. Using the background study and performing structural breakpoint tests the entire period was divided in to 5 meaningful periods. The second data set with daily open and close price of 289 companies were used for the clustering. Expected return and variance of each company in each period were used as the inputs for the clustering. K means clustering was used to achieve the main objective of clustering. When clustering the basic idea was to achieve meaningful clustering based on risk return tradeoff to facilitate better investment decision. Then the composition of clusters from period to period were analyzed with relevant to industry classification. The cluster analysis shows that first and second period in year 2019 before the covid pandemic can be divided in to 4 clusters. During covid first wave market can be clearly separated in to 4 clusters, during covid second wave 6 clusters and during the third wave 3 clusters. Some companies have performed unusually with high returns and high variance during covid first wave and third wave. Further by monitoring the shift of clusters from period to period set of companies were suggested as the high performing companies despite the covid pandemic for the Risk seeking investors. Another set of companies which obtain high returns during the pandemic by tolerating moderate level of risk were suggested for the Risk neutral investors. The remaining set of companies are suitable for the Risk Averse investors. Finally, the study concludes that there is an impact of the covid -19 pandemic for the number of listed entities in the stock market, composition of clusters and risk return level of individual companies at different stages of a Recession.
item: Thesis-Abstract
Collaboration modeling framework and trading portal for agricultural Products
Kithulgoda, CI; Jayaweera, PM
In Sri Lanka, the agricultural sector is the main source of livelihood of the rural population, which accounts for 70% ofthe total population. Although, the agricultural supply chain of Sri Lanka is full ofimperfections and hence inefficient. Meanwhile, several studies observed that the clear majority of small and mediumsized enterprises in Sri Lanka accept the importance of information and communication technology and e-commerce in their businesses. By considering these facts, we recognized the necessity of using e-commerce applications in agriculture sector in Sri Lanka. In this research we proposed trading portal environment to complete planning, identification and negotiation phases of an ISO open-edi business transaction in four agricultural product categories namely, vegetables, fish, spices and fruits for small and medium enterprises in Sri Lanka. Small scale software has been developed to facilitate businesses to present their business capabilities, orders and demands to world with zero or minimum intervention of intermediaries. In addition, the system enables automatic partner matching by exact matches, counter offers and collective offers. After the selection of business partner by his business profile, uploaded trade lead or partner matching results, seller or buyer has ability to negotiate with that potential business partner through the system. Finally, we demonstrated the connection between e-commerce system design concepts and our trading portal according to ISO/IEC 15944-1 conceptual business transaction events, UMM requirements meta-models and REA ontology.
item: Thesis-Full-text
Daily profit maximization using linear programming techniques: Sapugaskanda
(2015-08-26) Rajapaksha, RKMM; Cooray, TMJA
The petroleum industry plays one of the most significant role in the energy market in Sri Lanka. The actual use of this source is limited by economical, technological and political reasons. Crude oil refining is an extremely complex and dynamic activity since the refinery itself works to maximize its profitability under the frame work of the organization. To model the LP Problem to the Crude Oil Refinery station in Sapugaskanda, Sri Lanka, the primary data was collected. The data was modeled and the Linear Programming (LP) method was used to get the optimum solution. The refinery produces 12 major petroleum products together with 24 intermediate streams. The commonly used and most profitable products are Gasoline, SBP and Diesel. For above 36 streams, the flow rates in Metric Ton (MT) per day were considered as decision variables. To maximize the profit, the product values were considered as positive and the raw material costs and operating costs were considered as negative. The TORA software was used to generate the optimum solution. The optimum result obtained showed a notable profit compared to the existing situation in the Oil Refinery Station, Sapugaskanda. The operational difficulties, assumptions, suggestions and further recommendations were discussed.
item: Thesis-Full-text
Day effect in return and volatility of the selected sector indices in Colombo stock exchange
Karunananda, GACM; Dissanayaka, R
One of the significant anomalies of Efficient Market Hypothesis (EMH) is the seasonal effect. The existence of the seasonal effect implies market inefficiency. Most ofthe investors, especially international investors are more concerned with the market efficiency. The most common seasonal anomalies are the Day ofthe week effect, Day ofthe month effect, week ofthe month and the month ofthe year effect. According to past empirical studies Day of the week is the most talked anomaly among those. When the day of the week effect exists, investors can earn abnormal profit by buying the stock in low return day ofthe week and selling them at a higher return day ofthe week. In Sri Lankan context, all the studies on finding the existence of day of the week effects in stock return and volatility in Colombo Stock Exchange (CSE) are conducted for the whole market using All Share Price Index (ASPI). As all those studies mainly focused on ASPI and no studies focused on sector wise, this study examines the same problem focusing two sectors: Hotels and Travels (H&T), Investment Trusts (INV) in CSE. The daily returns for each sector over a period of two years from 2014 to 2016 are tested using three types of conditional time varying models, namely GARCH, EGARCH, and GJR-GARCH. The study finds strong evidence for the presence of day of the week effect in stock returns and in volatility ofthe two sectors. Among the five days ofthe week Thursday returns are negative in H&T and it is significantly higher than that of other days ofthe week. Only Monday returns are significant in INV and it is negative. While Monday volatility is significantly positive and higher than that of other days of the week in H&T, Thursdays and Fridays volatility are significantly different from zero and negative in INV.
item: Thesis-Abstract
Determination of electricity demand for Sri Lanka
Dayaratne, J; Peiris, TSG
Electricity has become important component in today’s life for everyone on earth. The demand for electricity has grown year by year with the growth ofindustrialization, population and urbanization. Hence, the importance to forecast electricity demand has become an inevitable need with great importance in order to plan country’s power production well in advance to avoid any hindrance to its economy. Using annual electricity demand from 1969 to 2008 as a training data set, three models: multiple regression model, Autoregressive Integrated Moving Average [ARIMA (1, 1, 0)] and trend model were developed to forecast annual electricity demand. All models were statistically tested and also validated using data from 2009 to 2011 as a validation set. Further long term forecast (2012 to 2016) were done using all three models and compared the forecast values given by the Ceylon Electricity Board (CEB) for the same period. The explanatory variables used for the multiple regression model are annual Gross Domestic Product and population ofthe country. By comparing the results for training set, validation set and for long term period (2012 to 2016), it was found trend model is statistically sound, more practical, feasible and user friendly. Thus, it is recommended to use the trend model for the future prediction. This model can be easily used by any policy makers without any other external variables.