The objectives of this research were to investigate risk factors for Dengue fever in Thailand and to select an appropriate model. The generalized estimating equation (GEE) whose dependent variable has a Poisson distribution and a negative binomial distribution were studied. The secondary data consisting of the number of Dengue fever patients rainfall average temperature forest area household income were collected. Regions and seasons were also considered. The research found that the GEE whose dependent variable has a negative binomial is more appropriate to be used for Dengue patient data analysis. Central region and the season during Feb-Apr were assigned to be reference groups. Risk factors for Dengue fever were rainfall (Relative Risk (RR) = 1.0009) average temperature (RR = 1.1736) forest area (RR = 1.0482) southern region (RR = 2.7390) eastern region (RR = 2.0489) western region (RR = 1.4051) the season during May-Jul (RR = 3.0526) and Aug-Oct (RR = 3.2677)

The objectives of this research are: to study the characteristics of students in the Faculty of Engineering at Rajamangala University of Technology Pra Nakorn North Bangkok Campus that influence to the risk of withdrawal from Calculus 2 for Engineers; to predict the risk of withdrawal from Calculus 2 for Engineers; and to use the results of the study for planning and solving the problems of withdrawal from Calculus 2 for Engineers. The sample is 226 students in the Faculty of Engineering at Rajamangala University of Technology who enrolled the Calculus 2 for engineers in the second semester of the academic year 2009. The data are from the questionnaire. The factors considered are grad point average the number of enrollments for the Calculus 1 for engineers Calculus 1 for Engineers grade the number of courses that emphasize on calculation that were enrolled in the second semester of the academic year 2009 the sacrifices of students for the Calculus 2 for Engineers course and the need to withdraw from Calculus 2 for Engineers course before other courses. The logistic regression model in which the parameters are estimated by using Bayesian methods is used for analyzing the data. The study shows that the factors that influence to the risk of withdrawal from the Calculus 2 for Engineers are grade point average Calculus 1 for Engineers grade the number of courses that emphasize on calculation that were enrolled in the second semester of the academic year 2009 and the sacrifices of students for the Calculus 2 for Engineers and the need to withdraw from Calculus 2 for Engineers before other courses. The factor that does not influence to the risk of withdrawal from the Calculus 2 for Engineers is the number of enrollments for the Calculus 1 for Engineers.