The purpose of this research was to construct the appropriate forecasting model for the export values of alcoholic beverages using three-time series analysis methods including Box-Jenkins method damped trend exponential smoothing method and combined forecasting method. Time series data from the website of Office of Agricultural Economics with total 199 months from January 1998 to July 2014 were used and divided into two series. The first 192- month data from January 1998 until December 2013 were used to build the forecasting models and the last 7-month data from January to July 2014 were used to compare the forecasting method accuracy via the criteria of the lowest mean absolute percentage error and root mean squared error. Research findings indicated that for all forecasting methods that had been studied combined forecasting method was the most accurate method and this model was when and represent the single forecasts at time t from Box-Jenkins method and damped trend exponential smoothing method respectively.

The purpose of this research was to construct an appropriate forecasting model for the export quantity of frozen and chilled chicken using three time series analysis methods including Box-Jenkins method Holt’s exponential smoothing method and damped trend exponential smoothing method. Time series data from the website of the Office of Industrial Economics with total 130 months during January 2004 to October 2014 were used and they were divided into two series. Fristly 120 months from January 2004 to December 2013 were used to build the forecasting models and lastly 10 months from January until October 2014 were used to compare the forecasting methods accuracies via the criteria of the lowest mean absolute percentage error and root mean squared error. Research findings indicated that all forecasting methods that had been studied damped trend exponential smoothing method were the most accurate method and showed the forecasting model as where m represented the number of periods to forecast ahead with the starting value was January 2014 (m = 1).

This research is the comparative study of three forecasting methods on SET 100 index. These methods are Simple Exponential Smoothing method Holts method and Box-Jenkins method. Two sets of data were used in this study. The first one used as a training set was collected from January 2 2008 to September 30 2011. The other one used as a testing set was collected from October 3 2011 to October 14 2011. We propose that the most appropriate forecasting method is the one which give the lowest MAE MSE MAPE and diagnostic checking. The results show that Holt’s method displays the lowest MAE MSE and MAPE. The next one is Box-Jenkins method while the Simple Exponential Smoothing method exhibits the highest value of all three indicators. However the model from Box-Jenkins method is the only one way that reveals no residual autocorrelation. This leads to the conclusion that the appropriate models for forecasting of SET 100 Index is ARIMA (213).

This research aimed to compare the techniques and method used to solve non-linear equations with SEM. By Partial Least Squares (PLS) technique and Product Indicator Approaches (PIA) technique. Were tested by the two methods of case studies is motive in the decision to study at Bachelor degree in Rajamangala University of Technology Suvarnabhumi Suphanburi campus Information Technology field. For sampling 221 found Partial Least Squares (PLS) technique to solve the problem of non-linear equation. However the same study Product Indicator Approaches (PIA) technique do not use this method as error indicators for the model with a negative value wrong predictions by SEM. Can not be predicted by the model to them.

The objective of this research is to propose a forecasting model for uncertain demand index data of steel. The forecasting model proposed by Yelland (2010) was modified by adjusting the prior distributions of some parameters in the model in order that it is suitable for the demand of steel in Thailand. The algorithms for model fitting were written in OpenBUGS. The proposed model was compared to a classical exponential smoothing model. The research found that the forecast errors from the proposed forecasting model were minimum.