This research aimed to study factors affecting the selection of accounting policies to measure the value of investment property of companies in the Stock Exchange of Thailand which related to earning management through discretionary accrual items. In this case the selection of these accounting policies were according to Thai Accounting Standard No. 40 : Investment Property. The sample size of this study was 239 listed firms in the Stock Exchange of Thailand who disclosed about investment property in their annual reports in 2015. Logistic regression analysis and ttest were employed to analyze data. The research revealed the debt to equity ratio was related to the selection of accounting policies to measure the value of investment property at 0.05 significant level. Furthermore the result from t-test found that cost model and fair value model for measuring investment property were not significantly different in earnings management at 0.05 significant level.

The objectives of this research were to study personal factors and cat product consumer behavior. To study marketing mix factors related to customer behavior included marketing mix factor related to cat product consumer behavior in Thailand metropolis. This research was combined 2 methods. Quantitative research: The samples were 400 consumers by using questionnaire as tool to collected data. Analyzed by using descriptive statistics to determine frequency percentage mean standard deviation Pearsons chi-squared test statistics on the statistical level significance of .05. And Quality research: The sample are opinion leader vendor and consumer by using Indepth interview to analyze relation between opinion vender and consumer conform to result of quantitative research.

The objectives of this research are to propose an approate and efficient model for analyzing rice corn and sugar yields data. A linear mixed model (LMM) with spatial correlation following the conditional autoregressive model (CAR) was adopted. The results show that for rice yields if the amount of rainfall in a harvest season increases 1 mm the yields will decease by 25.74 tons. if the temperature in the harvest season increases 1 Celsius the yields will decease by 212.60 tons and according to the trend the yield will increase by 15.80 tons each year. For sugar cane yields if the amount of rainfall in the harvest season increases 1 mm the yields will decease by 51.35 tons. if the temperature in the harvest season increase 1 Celsius the yields will incease by 121.30 tons and according to the trend the yield will increase by 29.93.80 tons each year. For corn yield if the amount of rainfall in the havest season increases 1 mm the yields will incease by 73.45 tons. if the temperature in he havest season increases 1 celsius the yields will decease by 40.44 tons and according to the trend the yield will increase by 1.74 tons each year.

The objectives of this research are to propose a proper model for risk assessment for drought in Thailand. A hidden Markov model is adopted. The results indicate that the amount of rainfall depends on the hidden states drought or non-drought state. If the state changes from drought to non-drought the amount of rain will increase. The probability of changing from drought state to non-drought state is higher than from drought state to drought state. The probability of drought occurrence in February is highest followed by in November March December January July April June October September August and May respectively. When the temperature increases the probability of drought occurrence will increase.

This research aims to apply the principle of stochastic process for modeling. The parameters are estimated using Bayesian methods. The monthly average real price of paddy rice 15% and yield of paddy rice in Thailand were studied. The price and the yield of paddy rice which are time series data consisting of four components autocorrelation an exponential cumulative distribution function for trend outliers and two different types of seasons: the dummy seasons and Fourier function seasons. Writing algorithms programming in OpenBUGS and evaluating the performance of models from simulation programming in R were conducted. After that Bayesian methods with dummy seasons and Fourier function season were compared using RMSE MSE and MAE as the criteria. The results show that the Bayesian model with an exponential cumulative distribution function for trend and dummy seasons give the lowest RMSE MSE and MAE for both model fitting and model validating.