RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
In this study, mainly through the assessment of the 2000 presidential election in Taiwan poll accuracy, to explore how the use of different assessment methods in different election. Since 2000, Taiwan's presidential election results show that the election of the election is between two main candidates and three major candidates "quasi - two main candidates," but whether the election should be different with different people tune the accuracy of the calculation method of assessment? In this study, modify Mitofsky and Traugott's method of assessment for 1996, 2000 and 2004 US presidential elections (two main candidates) polls show, put forward a more reasonable assessment applicable to Taiwan's 2000 presidential election polls approach. In this study, in addition to using the modified method for analyzing the performance of election polls, but also to further investigate the effect of differences in the accuracy of the polls by the empirical factor.