Tourism comprises of the activities of persons traveling to and staying in places outside their usual environment for not more than one consecutive year. Tourism is one of the major foreign exchange earners in Malaysia. Therefore, forecasting tourist arrivals becomes important because it would enable tourist related industries like airlines, hotels, food and catering services, etc., to plan and prepare their activities in an optimal way. Previous studies have suggested various time series models for modelling monthly tourist arrivals to Malaysia. Since then, new observations have become available and it is important to update these models. Therefore, in this paper we update and compare the performance of three time series models for modelling tourist arrivals to Malaysia. One of them is within the class of ARMA models and the other two are in the class of ARFIMA models