The previous studies focused on various aspects on Thai tourism; for example Chang et al. (2009) evaluated changes in tourism trends by applying Box-Jenkins autoregressive integrated moving average (ARIMA) models to obtain information of inbound trips and the trends in foreign tourist arrivals to Thailand. This study analyzed stationary and non- stationary tourist arrivals series by formally testing for the presence of unit roots and seasonal unit roots prior to estimation, model selection, and forecasting. Various Box-Jenkins ARIMA models and seasonal ARIMA models were estimated, with the tourist arrivals series showing seasonal patterns. The fitted ARIMA and seasonal ARIMA models forecast tourist arrivals from East Asia very well from the first quarter of 2006 until the first quarter of 2008. Total monthly and annual forecasts could be obtained through temporal and spatial aggregation. The study found seasonal unit roots in tourist arrivals from East Asia with varying seasonal patterns of tourist arrivals from all countries except Singapore.