Master of Science in Business Statistics

Permanent URI for this collectionhttp://192.248.9.226/handle/123/66

Browse

Now showing 1 - 20 of 69

item: Thesis-Abstract
Time series approach to model rates of inflation in Sri Lanka
(2023) Iroshani, WE; Mathugama, SC; Jayasinghe, JABU
Inflation can have a variety of effects on the economy, both positive and negative. The negative effects, however, are more severe and also include other negative financial features like as a decline in the real value of money. The uncertainty around the rate of inflation in the future may influence customers away. Moreover, it may result in a decline in foreign investment in a country. Finding a useful Arch-type model for predicting inflation in Sri Lankan inflation rates was the aim of this study because inflation can be highly volatile and volatility clusters also possible which indicates the appropriateness of fitting ARCH type models for the inflation series. Furthermore, there was no evidence in the literature to support the fitting of an ARCH type model. The performance of ARCH type models was examined using the inflation data from January 1990 to September 2022. Due to the non-stationary nature of the inflation rate series, the first differenced series was obtained and the transformed series was tested for ARCH effect. The test revealed that the inflation series contains heteroscedasticity and correlation. In order to choose the optimal model, the study used the AIC and BIC criterion. The ARIMA (1,0,2), GARCH (1,1) model with student t distribution was chosen to simulate volatility, while ARIMA (1,0,2) was chosen as the mean model to predict future inflation series. Keywords: Inflation, GARCH, volatility, heteroscedasticity
item: Thesis-Abstract
Organizational factors affecting e-commerce adoption in small and medium enterprises in Colombo district
(2023) Dissanayake, DKSM; Jayasundara, R
Modern world organizations need to maintain some sort of Electronic Commerce (EC) utilization in order to ensure the long-term sustainability of the organization. Not only the large-scale businesses but also the Small and Medium Enterprises (SMEs) which is the target group of this study practice it. The usage of EC in SMEs has grown in significance as a research area in information systems. Governments have paid a lot of attention to encourage SMEs to use E- Commerce, but few research has been conducted to evaluate the optimal E-commerce adoption strategies for Small and Medium Scale Enterprises in developing countries, notably Sri Lanka. This study's primary objective was to assess the correlation between organizational elements and the EC adoption. Quantitative methods were taken into consideration in this research in order to figure out the major elements that contribute EC adoption in Small and Medium enterprises. The information used in the study was acquired through a survey of 150 SMEs in the Colombo District. The sample was chosen using a stratified random selection technique based on SME-businesses. Results of this study, which were based on correlation and Consistent Partial Least Square Method. Some factors were illuminating and made it easier to comprehend some organizational characteristics that affect the degree of EC adoption. Top management support was the biggest factor found. The findings of this research lend empirical evidence to the idea that organizational characteristics and SMEs' adoption level of E-commerce are positively associated. The degree of EC adoption in SMEs and employee gender were also found to be negatively correlated. It might be argued that a gender that encourages creativity and risk-taking would offer the necessary support for greater adoption of new technology. The firm's business practices are influenced by the top management’s views on innovation. Key Words: SMEs, Factors, E- Commerce, Adoption, Colombo District, Organization
item: Thesis-Abstract
Factors influencing work life balance of G.C.E (O/L) and G.C.E.(A/L) teachers in Sri Lanka during COVID-19 pandemic a structural equation model
(2023) Edirisinghe, SI; Dissanayake, R
With conflicting responsibilities and commitments, maintaining a work-life balance in the office has grown to be a significant difficulty. The twenty-first century is characterized by constant change, uncertainty, and intense pressure to increase productivity. Today's high-tech world's fast-paced, multitasking lifestyle has created expectations for both personal and professional devotion. Working women are under a lot of stress because of their jobs, and they face many challenges and worries at work. At best, it can be challenging to strike a balance between one's personal goals and duties and one's professional obligations. Most previous research on juggling work and family revealed that women frequently shoulder more responsibility for both, making it more challenging for them to establish a balance at both ends. It is essential to consider how teachers' wellbeing affects students' experiences and achievements. This qualitative study examines the happiness of professors at public universities in Sri Lanka. The research takes place during the coronavirus disease (COVID-19) epidemic, when schools are strapped for cash and instructors are looking for a better work–life balance by working from home. Therefore, there is a theoretical gap between the previous research and the present study. The research uses a descriptive survey approach, positivism philosophy, and mixed method approach to identify the relationship between teach concerns and work life balance, job satisfaction mediating teacher concerns and work life balance, and job stress moderating teacher concerns and work life balance. Data was collected from 350 school teachers who teach Ordinary Level, and Advanced Level in government, semi-government, and private schools in Sri Lanka. According to this study, among instructors participating in COVID-19, family obligations may conflict with work obligations more frequently than the reverse. It was identified that because of the high workload and more urgent demands, one is forced to carry their job home with them, and demands of employment interfered with obligations to one's family. Additionally, the research identified that work-life balance is determined not only by the external pressures imposed by employers but also by the internal pressures brought on by the amount of motivation of the individual.Keywords: work-life balance, job satisfaction, Structural Equation modelling, job stress, COVID 19 Impact
item: Thesis-Abstract
Modeling USD/ LKR exchange rate using time series techniques
(2023) Hettiarachchi, PHTS; Dharmarathne, HASG
Modeling Exchange Rate is one of the most vital and essential parts of financial econometrics. This study aimed to formulate time series models using both univariate and multivariate time series techniques. The macro-economic factors of Inflation Rate, Trade balance, Net Foreign Assets, and Foreign Remittances have been used in this study which were chosen by an extensive literature survey. Data from January 2015 to October 2022 was used in this study. A univariate model was formulated using ARIMA and ARCH/GARCH modeling techniques. The GARCH model with the mean equation which is estimated by an ARIMA (1,1,1) Model along with a dummy variable and the variance equation which is estimated by GARCH (1,0) Model was selected as the best-fitted univariate model with a R-square value 81.8%. Using ARDL modeling technique associated with ARDL bound tests for cointegration was used to formulate the multivariate model. The ARDL (3,4,3,0,0) was selected as the best-fitted model which satisfied all the assumptions along with model specifications. It was identified that there exists significant co-integration among the exchange rate and the selected macro-economic factors. Error correction model was formulated based on the selected ARDL model and according to the results, the speed of adjustment is -5.78% which means that the short-run model will be converged to the long-run equilibrium by 5.78% for each period moving forward. Among the two models selected from univariate and multivariate analysis, ARDL (3,4,3,0,0) model was selected as the final best fitted model. Key Words: Exchange Rate, Advanced Time Series Analysis, ARIMA, ARCH/GARCH, ARDL, Cointegration
item: Thesis-Abstract
Factors associated with over expenditure among low income households in Sri Lanka
(2023) Kodithuwakku, AJ; Thissera, D
Over expenditure can cause various problems in household. If monthly income is lower than monthly expenditure it can be referred to as a situation of “over expenditure”. This means that the amount of money spent in a given month exceeds the amount of money earned during that same period. It can worst the living condition in a low income household. It can be identified huge problems in the society due to low income in the households. Among the problems caused by insufficient income are health problems caused by insufficient nutrition and depression due to the inability to provide adequate facilities for the dependents, economic security lost due to the increase in expenditure over income, negative impact of family well-being with mental stress and emerging family problems, negative impact on children‟s education, mental and physical health and the future etc. are critical social problems.so it is important to find out the reason for over expenditure among low income families. Therefore the current study was done in order to find the factors associated with over expenditure among low income families. This study was done by using secondary data obtained from the Income and Expenditure Survey_ 2019, conducted by Department of Census and Statistics. There are seven factors identified as significantly associated with over expenditure among low income households. Those are Sector of residence, Number of members in household ,Employment status of the household head, Educational level of the household head, Age group of the household head, Suffer from chronic illness by household head , monthly food expenditure greater than the half of income. Among low income households in Sri Lanka those who are in urban sector, working as a contributing family worker, headed by person who are in 31-40 year of young age level and suffer from chronic illnesses, have the maximum possibility of being low income over expenditure per month. Also the family who spent money for their monthly expenditure than their half of monthly income has high possibility being low income over expenditure. When increasing the number of family members possibility of being over expenditure also increasing. Keywords: Economic security, Family well-being, Family stability, Food security
item: Thesis-Abstract
Factors influencing the selection of banks for personal banking activities by employed people in Matara district
(2023) Jaliyagoda, ST; Jayasundara, DRT
The aim of this research is to investigate the factors influencing the selection of banks for personal activities by employed people in the Matara District which is the main commercial city of the Southern Province in Sri Lanka.The banking industry is continuously changing due to its current competitive nature. This industry tends to replace their traditional procedures with user-friendly and fully digitalized banking procedures that manage the high competition with other banks. Employed people in society have different attitudes toward the new trends in the banking sector. So, the goal of this study is to identify the variables that influence the choice of a bank for personal banking activities by employed people and make this information available to those who hope to choose a bank in the current context. This research used the convenient sampling method to collect data. Data were collected from randomly selected participants, who are employed in the Matara district, focusing on their perceptions and the criteria they use when selecting banks, and the factors that influence them to choose banks. The results showed that most affecting variable for selection of bank was their job category. Gender and education level were also found as factors affecting the selection of a bank among government and non-government banks for personal banking. The results will be helpful in preparing the strategic plans of the banks and it will be a guide for individuals to make banking easier for themselves. The implication of this research is bank management, academicians, and policy makers must devote resources and evaluate and redesign current marketing strategies in order to retain customers in the competitive bank environment in Matara district. Keywords: Customer Attitude, Customer Satisfaction, Trends in Banking
item: Thesis-Abstract
A Study on consumer awareness of single- use plastics and its association on their purchashing behaviour in Sri Lanka
(2023) Sanchitha KH; Tissera JHDSP; Jyasundara DRT
Plastic pollution resulting from widespread use of single-use plastics has emerged as a global environmental crisis, including in Sri Lanka. The study examines the awareness and behaviors of consumers concerning the environmental impact of single-use plastics and explores how demographic factors impact their awareness. It also investigates the relationship between consumer awareness and their willingness to make lifestyle changes to mitigate plastic pollution. Further, the study provides recommendations on effective strategies to increase awareness and reduce the usage of plastics. The study encompasses a diverse sample of 169 respondents aged 18 or above, collected by snow-ball sampling, while highlighting the need for balanced representation across resident districts. Participant’s awareness level of single-use plastics was quantified by scoring their responses in Section 2 of the questionnaire. Key findings indicate strong positive correlation between education and awareness. Consumers with higher education are more likely to be aware of the environmental effects of single-use plastic fostering an increased willingness to make lifestyle changes to minimize pollution. Considering the limited population in Sri Lanka with a higher education, the importance of targeted awareness programs embedded in school curricula and public programs targeting different age groups is highlighted. The study emphasizes the crucial role of government, businesses, and consumers in mitigating plastic pollution. Collaboration with government and businesses is encouraged to find sustainable alternative packaging and establish widespread collection facilities. Introducing new legislatives on tax and bans are recommended for reduction in plastic consumption. Consumers are encouraged to incorporate sustainable daily habits and participate in environmental clean-up initiatives. This study advocates a comprehensive approach to address single-use plastic pollution in Sri Lanka, emphasizing targeted awareness campaigns and collaborative efforts among stakeholders. By implementing these strategies and fostering a culture of responsible plastic usage, Sri Lanka can pave a future with sustainable practices and cleaner environment.
item: Thesis-Abstract
Development of an index to compare the Colombo stock exchange registered companies based on stock prices volatility and systematic risk effect
(2023) Lelwala, HC; Liyanage, UP; Jayasinghe, JABU
Managing the risk is a key element in portfolio analysis and many studies have been done to identify the impact of the risk into stock market investments. It allows the investors to consider the potential downsides before making choices on investments. The study aims to help investors by making it easy for them to make informed decisions on how to diversify their portfolio while minimizing the risk that it inherits. The dataset has been taken from Colombo Stock Exchange and it has data from 2016 January to 2020 December for 19 sectors. The dataset includes 264 companies, 239080 instances and quarterly systematic risk values for each sector. In this study we are using statistical methods such as K Means clustering, Pool regression and time series decomposition. In the first method study is providing an algorithm to identify the clusters in a sector to minimize the risk by allocating the investment into different clusters within the same sector regression. The second method uses a pool regression model to find out if there is any relationship between the systematic risk and the residual values that have been taken from time series decomposition in a sector. In the third method a new index has been introduced to cluster the sectors in CSE by using systematic risk and residual values. The first method provides clustering results based on stock price volatilities for each sector. This method is best suitable for an investor that is interested in allocating the portfolio in one sector in CSE. The results of the second method are showing that out of all the 19 sectors in CSE 12 sectors have a correlation between the systematic risk and the residual values that have been taken from time series decomposition. Final method is providing a new index that has been used to cluster the 19 sectors in CSE. This method can be used to diversify the portfolios in a wide range of stocks that will help investors to manage their risk efficiently. The sector clusters is confirmed with the correlation table which was obtained using the stock prices in each sector.
item: Thesis-Abstract
Analysis of factors underpinning the voting behavior of Sri Lankans under the current economic crisis
(2023) Wathsala, WADR; Jayasinghe, JABU
Voting is the most common and effective way of political participation across the globe, as it showcases the willingness of voters and the fate of a country. It serves as a powerful tool to hold leaders and political parties accountable for their actions. To analyze voting behavior of general public a combination of crucial factors can be taken into account, such as voter satisfaction with recently elected candidates, reasons for voting during next elections, the influence of the ongoing economic crisis on political decision-making and identifying preferred candidate characteristics. To carry out the research, a convenience sampling method was used to select 418 voters and employed Descriptive Statistics and Factor Analysis methods for the data analysis. The Principal Component Analysis method with rotation exhibited the highest level of accuracy in factorization. The findings revealed a prevailing sense of dissatisfaction among voters with the recently elected candidates, while the level of satisfaction was found to be significantly associated with voters' previous voting experiences. The majority believes that the economic crisis has altered their political thinking patterns, and their primary motivation for casting their vote in the next election is to choose a candidate capable of addressing the current economic crisis. Additionally, Factor Analysis revealed five key candidate characteristics that voters prioritize when selecting a suitable candidate.
item: Thesis-Abstract
An Analysis of trade dynamics of Sri Lankan tea exports
(2023) Dissanayake, AKA; Abeysooriya, RP
Tea exports significantly contribute to the Sri Lankan economy since it is one of the major agricultural export crops in this island nation. Even though Sri Lanka is one of the leading tea exporting nations in the world, the percentage share of Ceylon tea in the global tea market has been gradually decreased over the years. With this background, this study aims to comprehensively investigate the growth patterns, instability, influential factors, and future predictions of tea exports to propose recommendations to improve the tea export industry in Sri Lanka. Secondary data were mainly used in this study. The Compound Annual Growth Rate Analysis was employed to measure growth rates in production and exports of Sri Lankan tea while instability in production and export indicators of tea in Sri Lanka were calculated by using Cuddy Della Valle Index. The Sri Lankan tea export quantity was modelled and predicted by applying forecasting techniques as Seasonal Autoregressive Integrated Moving Average, Gaussian Hidden Markov Model, and Multilayer Perceptron. Sri Lankan tea exports has shown negative growth while tea export value has depicted positive growth during the period from 2011 to 2022. In the same time Iraq was the most stable market for Sri Lankan tea exports. The comparison of the prediction accuracy of various forecasting techniques in tea export quantity prediction was revealed that the Multilayer Perceptron was performed better than other techniques employed in this study. Tea export types as bulk tea, tea packets, and tea bags as well as year majorly affect on the future predictions of Sri Lankan tea export quantity in order to the data series which was applied for this study. The study findings will be useful for researchers, policy makers, exporters, and other relevant authorities. Further research efforts are recommended to do for tea export prices and earnings.
item: Thesis-Abstract
Modeling and forecasting the fabric demand in apparel industry: a statistical approach
(2023) Prerera, WAKT; Mathugama, S
The competitiveness in the apparel industry is continuously accelerating, thus, demand forecasting plays a vital role in decision making. The effectiveness of the decisions helps to increase profitability and customer satisfaction by reducing the risks in business activities. A well-recognized garment manufacturing company which supplies garments for a world-renowned sports brand was selected in this study. On Time Performance of the factory was found to be considerably reduced by over-forecast or below-forecast and hence influence the rating of the Factory’s performance. The main aim of this study was to model and forecast accurate future demands for selected fabric category. Secondary data was collected for the study using bi-weekly actualized customer demand and the sample covered data from December 2019 up to February 2023, summing up to 76 data points. Minitab software was used for descriptive data analytics and R statistical software package was used for the time series modelling. According to the descriptive data analysis, year by year, the demand was increasing exponentially. The summer season demand was significantly lower than that in other seasons. When it comes to the monthly demand, April, January and August months showed the highest demand and considerably low demand in February, October and November months. If buy-wise demands were considered, April 2nd, August 2nd, June 2nd, January 2nd and April 1st buys have the highest demands respectively. Demand is very low in February 2nd and October 2nd buys. Among the fitted ARIMA models the ARIMA(4,1,4) model with non-zero mean was identified as the best-fitted model. Model diagnostics confirmed that the selected model is well-fitted. The results indicate that the forecasting performance of the selected model is highly accurate with expected accuracy level for the immediate next 3 buys with a mean average percentage error of 6.85%.
item: Thesis-Abstract
Optimizing the water distribution network considering future demands in a suburb area in Hambantota district in Sri Lanka
(2023) Wijesinghe, IE; Jayasundara, DRT
Water distribution system is a source of hydraulic engineering that conveys water from the source to consumers. Analyzing and designing the optimal dimensions of the pipes and pumps, which distribute water, are essential in order to make the system more efficient and less costly. Therefore, the objective of the research is to design a network to find cost-effective branched water distribution network while satisfying the water demand and pressure at each node. This study presents two approaches for designing a branched water distribution system that minimizes costs. Three cost functions are considered: cost of constructing the pipe, pumping station cost and the cost of the energy necessary for the pumps. Linear Programming(LP) is an optimization tool used to determine the optimum cost for hydraulic systems. First model was solved by using LP technique while satisfying all the constraints applied to a rural water supply network located at Lunugamvehera, Sri Lanka. The pipe diameter was regarded as the decision variable, whereas the pipe energy, total length, non-negativity of length, and pumping head were the constraint requirements. Each pipe network's required demand is calculated and anticipated for future population growth. After the model has been developed, the results are compared to the current engineering design. In the obtained optimal solution pipe P-4(300mm and 400mm) and pipe P-5(300mm and 400mm) consists of two segments of differing diameters. As per current specifications, each link's whole length is utilized for a single pipe diameter. Splitting the pipe into two sections has not been considered. According to the analysis, the optimal cost resulted in is Rs. 1 778 443 113.36. The second model was developed for the water distribution network optimization using Integer Linear Programming (ILP). According to the analysis, 1 935 627 000.00 rupees was the best solution obtained using the ILP method. However, the estimated total cost of the network in accordance with the engineering design is Rs. 2 065 278 912.18. This study reveals that each link can consist of any number of discrete pipe diameters to optimize water distribution system using LP technique, and pipe diameters and pump characteristics can only be determined using the zero-unity variable by the ILP technique. Therefore, these two models are economically more viable than the existing method used by engineering design. The results indicate that the proposed two models are guaranteed to be the optimal and gives the practical solutions for the integrated water network design.
item: Thesis-Abstract
Factors associated with youth unemployment and new trends of employment in Sri Lanka
(2023) Shyaminda, TVP; Magalla, CH
Youth unemployment is a significant issue in our country. This thesis aims to analyze and uncover the factors influencing youth unemployment and the requisite skills for Sri Lanka's growing industries, which are poised to become dominant sectors in the next decade. Data was sourced from the Varite Research and USAID Labour Market Assessment Survey conducted in 2018, with a specific focus on youth data as secondary data. The survey involved 2040 respondents, constituting 86.6 percent of the youth population, and followed the 2012 Census of Population and Housing sampling framework. Utilizing Pearson's Chi-square test statistics, the secondary data revealed a Significant association between most factors and youth unemployment. Interestingly, apart from English Reading Ability and Basic and Advanced Computer Skills, the remaining 18 variables, such as Presentation Skills, Customer Handling, and Sales Skills, exhibited a substantial influence on youth unemployment. Employing the Factor Analysis Method, these 21 variables (above mentioned) were categorized into four common factors: English and IT Skills, Communication Skills, Interpersonal Skills, and Technical Skills. Furthermore, through the application of the Cluster Analysis Method, the study concludes by identifying the main skills needed for each of the growing sectors: Tourism, ICT/BPO, Healthcare, Construction, and Light Engineering. The study underscores the demand for Technical Skills in Construction and Light Engineering, the significance of Interpersonal Skills in the Health sector, the importance of English proficiency in Tourism, and the critical need for IT skills in the ICT/BPO sector. These findings carry implications for the government's long-term developmental strategies.
item: Thesis-Abstract
A Binary integer linear programing model for the teacher allocation problem referring to pshycological factors for the Sri Lankan schools
(2023) Wanniarachchi, HWRD; Abeysooriya, RP
Many schools face challenges in optimizing their school timetables. Every school has its own set of criteria and limitations that are based on numerous elements such as number of teachers available, teacher competencies, number of subjects teach, time periods restrictions for academic lessons, and regulations established by the education authorities, etc. This study has two goals. First, consideration of practical constraints to the Sri Lankan school timetabling problems. Second, investigate the applicability of solving that problem to the optimality considering those practical constraints. By far, the exact optimisation methods have been rarely applied to school timetabling problems in the past studies. This dissertation reviews those approaches in literature and investigates how well an Integer Programming (IP) optimisation approach performs for a set of selected timetable problems. After reviewing literature and a field study conducted in Southern province schools in Sri Lanka, the study presents four versions of IP optimisation models. 1) IP model focused on maximizing overall competency level of teachers with 10 basic constraints, 2) IP model focused on minimizing unfilled demand of teaching requirements with 10 basic constraints, 3) Extended version of model 1 with another 5 different practical constraints, 4) Extended version of model 2 with another 5 different practical constraints. The models were solved using the computational power of IBM ILOG CPLEX optimisation studio. In order to compare the performance of solving, four different timetable problems were used as data instances. The proposed methodology and tools were found to produce optimal timetable solutions within reasonable times for the loaded instances. While reaching the objectives of the study, the study successfully evaluated the applicability of different constraints arise in timetable preparations, using the proposed IP model and solving procedure
item: Thesis-Abstract
Identifying the factors affecting the quality level of services in enterprise resource planning consultancy services - a case study on post implementation support
(2023) Wickramarachchi, AP; Dias, P
Businesses commonly seek support from Enterprise Resource Planning (ERP) consultancy firms to evade the risk of ERP implementation failure. These consultants are involved in both implementation and post implementation phases. The aim of this study is to identify the factors that impact service quality in post implementation ERP support. A structured questionnaire with 46 questions was used to collect the data from 87 consultants working in a consultancy firm. The questionnaire consisted of 8 general questions related to the background of the consultant and 9 independent variables (Knowledge of the Consultant, Job satisfaction, Clear communication of the Service Level Agreements (SLAs), Internal communication, Project Management techniques, Customer culture, Customer knowledge, Clear communication of the incident, X first level support strength within the customer organization) and 4 dependent variables (Responsiveness, Reliability, Goodwill, Escalations) were considered. The 9 independent variables were further segregated in to two factors as internal (Consultant Knowledge, Job satisfaction, Clear communication of the Service Level Agreements (SLAs), Internal communication, Project Management techniques) and external factors (Customer culture, Customer knowledge, Clear communication of the incident, First level support strength within the organization).Correlations among independent and dependent variables were studied and it was identified that each of the 4 dependent variables had a significant correlation between each of the independent variable identified except for the correlation between Responsiveness and Knowledge level of the consultant variables. From the 9 independent variable 2 internal independent variables (Knowledge of the consultant and Clear communication of the SLA s) and 3 external independent variables (Customer knowledge, Clear communication of the incident, first level support strength) were identified using Stepwise Regression analysis to explain the variability of the dependent variables (Responsiveness, Reliability, Goodwill, Escalations). Therefore, it can be concluded that both internal and external factors are important to maintain the service quality..
item: Thesis-Abstract
Improving transparency in supply chain for better brand performance :a statistical approach
(2022) Wijesiri MSI; Mathugama SC
The competition of the economic environment is increasing rapidly and it has been a prevailing issue in many businesses to achieve the balance between the supply and demand. This issue is further increased when there is a lack of transparency in the supply chain both internally and externally. Proper analysis on how to mitigate the gap of lack of transparency would lead to better performance of the business. Various time series forecasting analyses with the soft computing of neural networks can be utilized to hinder the gap of supply chain transparency. Further, application of queuing theory for the complete process enables to mitigate the issues created due to lack of transparency in the supply chain process. In this study, the focus was to improve the transparency by in depth study of produced and sold garments of a particular style in a global brand. The quantities of produced and sold were taken from a leading manufacturing company in Sri Lanka. The study was carried out with both time series analysis and queuing theory. For time series analysis, decomposition method, ARIMA method, VAR method have been applied. The VAR model was statistically adequate where models were derived for manufactured and sold quantities. Application of queuing theory has been carried out to understand the finished good quantity that would be stored in the warehouse before selling it to the consumer. Apart from that, a mathematical model has been carried out to identify the extensive stocks that were stored in the warehouse with a percentage reduction. This mathematical model could reduce further stock amount and thereby lead to better financial performance as well. The final short-term solution of stock reduction model is helpful to reduce the stock that will be stored in the warehouses and also opens for more holistic queueing modelling in future.
item: Thesis-Abstract
Factor influencing female labour force participation in Sri Lanka :
(2021) Kariyawasam KLGA; Jayasundara DRT
This study attempts to identify factor influence on Female Labour Force participation in Sri Lanka using Chi- Square test to identify important variables for the model and then binary logistic regression analysis to identify and to quantify the determinants of labour force participation. The study draws data from Sri Lanka Labour Force Survey 2019 conducted by the Department of Census and Statistics. The analysis investigates the data in order to find out the overall behavior of the labour force statistics and seeks the relationship between FLFP and explanatory variables. Eleven independent categorical variables are considered. Chi – square analysis for each variables divulge that all the variables considered have a significant impact on female labour force participation. The significant factors are age group, marital status, ethnicity, religion, relationship to head of the household, sector, level of education, province, literacy in English, currently attending to an educational institute, and number of dependents in the household. The results obtained in this study can be effective used for policy planning and economic planners can also identify growth sectors and analyze the job descriptions to pinpoint those areas which require appropriate female skill
item: Thesis-Abstract
Determinants of passenger satisfaction using public transport system in Colombo: a case study on Kottawa - Pettah route
(2021) Udayaseelan T; Peiris TSG
This research intends to identify the determinants of passenger satisfaction using the public bus transport system on Kottawa – Pettah Route in Sri Lanka. Data were collected from a structured questionnaire and the sample size is 400. The sampling method was stratified random sampling and a sampling unit is a passenger boarding from the Kottawa bus stand during November 2019. The Factor analysis (FA) was carried out to derive the inferences of the study. It was found that the observed data satisfied all the necessary requirements for FA. Fifteen factors identified as the determinants of satisfaction of passengers using Kottawa – Pettah Route. In view of the above, it is recommended to strictly implement the current laws and regulations, design new laws and regulations, train bus crew, introduce new innovative methods to improve the satisfaction of the passengers using public bus transport system. This will also result in protection and enhancement of the interests of passengers, other road users, drivers, conductors, operators and other stakeholders of public bus transport system in Sri Lanka.
item: Thesis-Abstract
Modelling child mortality via discriminant analysis and logistic regression
(2021) Kande Arachchi AKMDP; Peiris TSG
Prevalence of deaths of children has particularly become a global concern in strategic decision making in the field of health sector. In Sri Lanka, the risk of deaths at childhood period was higher during the past few decades. Many studies have concerned about the child mortality in various perspectives. The purpose of this study is to find the significant factors on under-five mortality and to recommend a most suitable statistical model to predict the child mortality, under aged 0-5 years of age. The secondary data was collected from the demographic and health survey (2016) conducted by the Department of Census and Statistics (DCS), Sri Lanka. Two types of statistical models: linear discriminant model and binary logistic model are statistically evaluated. Two models were evaluated with classification accuracy, ROC curve, sensitivity/ specificity and sample size variations. Both methods found that, gender of child, marital status, mother’s literacy, status of antenatal care, delivery type, pregnancy duration and decision-making ability are significantly influential variables (p < 0.05) on the status of child mortality. According to the classification results produced by models, discriminant model correctly classified the 89.6% of grouped cases and binary logistic regression model correctly classified the 94.6% of grouped cases irrespective of the status of child mortality. With respect to the all seven indicators, it was found that binary logistic regression model was more efficient and more effective than linear discriminant model. The inferences derived can be effectively used for strategic decision making in the health sector for reducing the child mortality in the future.
item: Thesis-Abstract
Modelling of traditional family planning usage by women in Sri Lanka
(2021) Karunarathne HVVMP; Peiris TSG; Edirisighe PM
Family planning plays a crucial role in enhancing the health of the mother and the child. Contraceptives are used by most women in the reproductive age span (15- 49 years). Sri Lanka has named as one of the countries with high usage of traditional family planning (TFP) methods than the other Asian countries. However, the reasons for that were not been investigated. Therefore, this study is carried out to identify the significant factors influencing on usage of traditional family planning by using data from Sri Lanka Demographic and Health Survey in 2016 and the sample size is 10835. The modern family planning methods are used by 83.7% women compared to the traditional family planning methods. Among the traditional family planning users, rhythm method is more popular (57.1%) than the withdrawal method (34.9%). The highest percentage of both the traditional and modern family planning methods are used by the women of age between 31- 42 years. A binary logistic regression model was developed to capture the factors which influence on the use of traditional family planning methods. The model was invariant on the type of selection method and selection criteria. The overall predictive power is 82.9%. The knowledge on family planning, having advice from public health midwives, attendance to well women clinics, religion, ethnicity, decision to use Family Planning, husband's occupation, women's age, women's occupation, women's education level, number of children, and wealth quantile are significantly associated factors with the usage of traditional family planning. The odds of the usage of TFP among the women having no children and women having 1 or 2 children are respectively 1.4 and 4.0 times higher than the women having 3 or more children. The factors identified are geared towards providing a contemporary, robust evidence base, therefore the key population groups in need of contraceptive services can be targeted more effectively and efficiently. Organizing counselling programmes and promotions on family planning and conduct media awareness programmes to avoid some myths on modern contraceptives can be suggested