The objectives of this research are to propose a model for estimating and detecting rice yields in Thailand to investigate the factors related to the rice yields to find the trend and to construct the maps of rice yields in Thailand. A linear mixed model (LMM) including the spatial effects which follow the conditional autoregressive model (CAR) and the time effects which follow the first-order linear autoregressive (AR(1)) model is proposed. The estimated rice yields are used to construct the rice yield maps in Thailand. The dependent variables are the rice yield in each month of each province. The factors considered are rainfall average temperatures and regions. The results indicate that the factors enfluencing the rice yields are rainfall average temperatures and regions (North Northeast South East West Central region is a refrence region). The trend also effects the rice yields. The rice yeilds maps are easy for readers to identify which areas have high or low yields and easy to compare the yields among areas by looking at their different colors.

The objectives of this research are to propose a model for risk assessment of Measles and Rubella morbidity in Thailand to investigate factors influencing on the Measles and Rubella morbidity rates and to construct the disease maps of those two diseases. The generalized linear mixed model (GLMM) in which the responses have a Poisson distribution and the spatial effects follow a multivariate conditional autoregressive model (MCAR) are adopted. The dependent variables are the number of Measles and Rubella disease patients in each province. The factors considered are average temperature the amount of rainfall and regions. The results show that the temperature rainfall and regions influence on the Measles and Rubella morbidity rates. Measles and Rubella maps are easy for readers to see which areas are at high risk and to compare the morbidity rates among those areas by looking at those different colors.

The objectives of this research were to propose a model with some functions including CAR spatial effects and to select a proper model for predicting rince and rubber yields in southern provices of Thailand. A linear mixed model (LMM) with spatial effects and dummy varables and Fourier seasonal effects was proposed. Bayesian estimation was used and the estimated rice and rubber yields were used for prediction. The dependent variables were rice and rubber yields in southern provinces of Thailand. Factors considered were rain temperature soil fertilizer soil organic matter trend and also sesonal effects. The results show that rain temperature soil fertilizer soil organic matter trend and sesonal effects influence on rice and rubber yields. The proposed model with Fourier seasonal term is the most appropriate comparing to the model with dummy variable for season effects and the Holt-Winters model. Therefore the proposed model with Fourier sesaonal term should be the first consideration for prediction.

The objectives of this research are to propose a linear mixed model including spatial effects to present the distribution of air pollution of each gas being Sulphur dioxide (SO2) Nitrogen dioxide (NO2) Carbon monoxide (CO) and Ozone (O3) and particulate matter (PM10) and to investigate the factors related to those air pollution in each area of Bangkok Metropolitan Region. The spatial effects are assumed to be a conditional autoregressive (CAR) model. The dependent variables are the amount of SO2 NO2 CO O3 and PM10 in each area and the independents considered are Industrial area business area and suburb area. The results indicate that the factors influencing the amount of air pollution ranking from most to least are industrial area suburb area and business area respectively.

The objectives of this research are to propose a linear mixed model (LMM) with spatial correlation for an analysis of rice yields in Thailand to estimate the rice yield in each month of all provinces in Thailand to investigate factors influencing on the rice yields and to construct the maps of rice yields. A linear mixed model (LMM) in which the spatial effects follow the conditional autoregressive model (CAR) is used. The estimated rice yields are used to construct the rice yield maps. The dependent variables are the rice yield in each month of each province. The data are secondary data at a provincial level. The factors considered are rainfall averaged temperatures and regions. The results show that the factors influencing on the rice yields are rainfall averaged temperature and region. The amount of regional effects ordering from largest to smallest values are northestern region southern region western region central region eastern region and northern region respectively. The top ten provinces and months with high yields ranking from largest to smallest values are Ubon Ratchathani in November (1328000 ton) Surin in Novermber (1070000 ton) Si Sa Ket in Novermber (1023000 ton) Buri Ram in November (939400 ton) Nakhon Ratchasima in November (907500 ton) Roi Et in Novermber (852800 ton) Chiang Rai in Novermber (769800 ton) Khon Kaen in Novermber (692800 ton) Maha Sarakham in Novermber (676200 ton) Udon Thani in Novermber (620600 ton) respectively. The rice yeilds maps are easy for readers to identify which areas have high or low yields. They are a useful tool for planning decision making and implementing plans to help rice famers to increase their rice production.