Browsing by Author "Hewapathirana, T.K."

Now showing 1 - 9 of 9

A statistical analysis of the monthly mean maximum air temperature in Colombo, Sri Lanka
(Journal of Science of the University of Kelaniya Sri Lanka, 2003) Hewapathirana, T.K.
The present study was carried out to fit a mathematical model to describe the variation pattern of monthly mean maximum air temperature in Colombo in order to predict the future values. Monthly mean maximum temperature values for a period of over 35 years were used for the analysis : Time series statistical methods were considered to study the trend and seasonal , cyclic and irregular components. The long term pattern in tlie variation of,monthly mean maximum temperature in Colombo appears to be dominated by a pronounced seasonal effect. The highest seasonal effect was found to be in March . It was found that the temprature of a particular month depends on the lagged temperature values of the two preceding months.
An evaluation of the performance of undergraduate students at the university examinations in relation to selcetion criteria - a case study in statistics at the University of Kelaniya
(Journal of Science of the University of Kelaniya Sri Lanka, 2003) Hewapathirana, T.K.
Students are selected to follow Statistics and Computer Science as a subject at the University of Kelaniya on the same criteria used by the University Grants Commission to select students to Science based streams of the Universities. As such 40% of the students are selected on island wide merit on their performance at the G.C.E (Advanced Level) examination , 55% on district basis and 5% from the underprivileged districts. The G.C.E (Advanced Level) aggregate mark or the z-score is high in the first group of students , and is low in the last group of students. The objectives of the present study were to determine whether the students who were selected on merit basis do better in the university examinations than the other students and to determine whether the students selected from underprivileged districts do not perform as good as the other students at the university examinations with respect to Statistics course units. The statistical analyses were performed using one way ANOVA, multiple regressions and simple linear correlations. The results indicated that there is no significant correlation between G.C.E.(Advanced Level) results and the performance at the subsequent university examinations in Statistics course units.The low performance of the students of underprivileged districts at the G.C.E (Advanced Level) examination appears to be due to low facilities for education prevailing in these districts. Given the same facilities and opportunities the students from underprivileged districts perform equally well at the university examinations of Statistics course units as the students who get better results at the G.C.E. (Advanced Level) examination.
Analysis of rainfall data at Kurunagala: A Stochastic approach
(Faculty of Graduate Studies, University of Kelaniya, Sri Lanka, 2002) Hewapathirana, T.K.
Development of a Minitab Macro Program as a Remedy to Overcome Heteroscedasticity in Linear Regressions
(University of Kelaniya, 2008) Attanayake, A.M.C.H.; Hewapathirana, T.K.
Homoscedasticity in the disturbance terms that appear in a regression function is one of the key assumptions of ordinary least squares analysis. As the developed regression model relies heavily on the model assumptions, violation of the assumptions severely affects the importance of a regression model. Transforming the response variable is one solution to overcome the problem of heteroscedasticity. Today most statistical packages use graphical methods to detect heteroscedasticity. Although a graphical method could be considered as a good starting point, no measure of reliability can be attached to inferences derived from a graphical method. In this study we have developed a Minitab macro to detect heteroscedasticity present in the disturbance terms by the use of graphical as well as statistical methods including the popular White's General Heteroscedasticity test and how to solve the heteroscedasticity problem by applying the alternative form of the Box-Cox power transformation. The alternative form of the Box-Cox transformation is given by: V= Yln(Y) A=O Where lnY= n-'I lnY; Considering the stability of V for minor changes in the power parameter A, the transformed variable, V is chosen for the analysis and useful values of A were found to be in the range [-2, 2]. The program was developed using a Local macro structure and tested on Minitab version 14 and requires Microsoft Windows 2000 or XP operating system to implement this program. The developed macro was tested for many data sets and was found that the program is capable in handling the heteroscedasticity present in the error structure.
Examination Performance of Undergraduates in Relation to Attendance at Lectures
(University of Kelaniya, 2005) Hewapathirana, T.K.
Formal sector financing on the marine fish production and socio-economics of fishers in Sri lanka
(The University of Sri Jayawardena Pura, 2001) Wijeyaratne, M.J.S.; Weerasooriya, D.; Hewapathirana, T.K.
Prediction of monthly mean minimum temperature at Nuwara Eliya
(Faculty of Graduate Studies, University of Kelaniya, Sri Lanka, 2002) Hewapathirana, T.K.
The association among the factors that influence students in getting private tuition at the G.C.E.(A\L) examination
(Proceedings of the Annual Research Symposium 2005-Faculty of Graduate Studies, University of Kelaniya, 2005) Hewapathirana, T.K.; Withnage, C.A.P.
The G.C.E.(Advanced Level) is the only exanJination in Sri Lanka that paves the way to free higher education. Hence, this examination has become one of the most competitive examinations in Sri Lanka. Most of the students who study for the G.C.E (A\L) examination seek the assistance of Private tuition classes. Therefore it seems necessary to identify the interaction among the factors that influence students in getting private tuition for the Advanced Level Subjects. Hence, this study Was cal Tied out in order to explore the relationship between various reasons that influence students in attending private tuition for the G.C.E.(A\L) examination. The data for this study were collected by administering a questionnaire survey among a sample of 312 students who entered the Physical Science stream of the University of Kelaniya in the academic year 2002/2003. The seven influential factors that compel students in getting Private tuition for the A\L Subjects viz. gaining additional knowledge, associating with friends, covering the entire syllabus, parental influence, tense competition to get into a local university, attractive teaching pattern of the teacher and association with fiancee/fiance Were Considered as variables in this study. According to the Pearson’s chi-square test, most of the variables were found to be associated with each other. Hence, a more advanced log-linear modeling approach Was Used to explore the relationship between the categorical variables considered in this study. Model selection was done using the SAS statistical package and the goodness of fit of the model was tested using Pearson’s likelihood ratio Chi square test statistic. The best model which mostly influences students in getting Private tuition selected by the forward step wise method that could be used to model cell counts in terms of the associations among the variables Was found to Contain six partial associations. According to the study it was revealed that students who participated in tuition classes mainly due to their parents influence have done so either to have association with their fiancee /fiance or friends. Most of the students who attended private tuition classes to have association with friends have also taken into accountant the attractive teaching pattern of the teacher. Those students who participated in private tuition classes in order to cover the entire syllabus have not taken in to account the attractive teaching pattern of the teacher but however have considered the fact of gaining additional knowledge .It was also revealed that those who attended due to tense competition to get into a university have also considered the attractive teaching pattern of the teacher
A Univariate Box-Jenkins Model to Predict Relative Humidity Levels in Puttalam at Night
(University of Kelaniya, 2008) Attanayake, A.M.C.H.; Hewapathirana, T.K.
Humidity is among one of the most important weather conditions that influence salt preparation. Technical processes and treatments carried out in salt factories and laboratories require relative humidity levels to be maintained using control systems. Puttalam is a reputed saltern in Sri Lanka. The knowledge on the fluctuations of relative humidity is paramount for the management of Puttalam saltern, to carry out their activities in a proper manner. This paper presents the results of a study carried out to develop a prediction model for relative humidity during night time in Puttalam saltern, using Box-Jenkins methodology. This study is based on percentage mean relative humidity data collected from the Puttalam weather station from January 1998 to December 2007. Sample autocorrelation functions and sample partial autocorrelation functions are used as the major diagnostic tools in this model building procedure. Model parameters were estimated using the non-linear least squares method. The adequacy of the fitted model was checked by analyzing the residuals. According to the analysis it was revealed that the ARIMA (1, 0, 1) (1, 1, 1\2 model is the best model that could be used to forecast the percentage mean relative humidity at Puttalam saltern during night time. Forecasts can be readily generated using the above model up to a period of twelve months without using any external variables.