Search

This article focuses on identifying the variable which has the highest predictive power in predicting electoral behaviour. To do this, we apply a tree-based machine learning technique to data from Malaysia's 14th General Election. We find that constituencies' urbanization level has the most significant predictive power in determining vote share. Ethnicity, a long-touted variable of significance, plays a secondary role. Moreover, these predictors' marginal effects on the vote share are highly complex, non-linear and difficult to pick up by conventional regression [End Page 461] methods. Other explanatory factors do not exhibit significant predictive qualities of electoral behaviour, although the extant literature has shown them to have important causal relationships. As our analysis reflects the significant predictive power of urbanization in predicting voting behaviour, we caution against the haste to dismiss its relevance in the Malaysian context. [ABSTRACT FROM AUTHOR]

The 14th Malaysian general elections (GE14) resulted in a regime change not experienced since independence. While ethnicity has been an overriding factor in determining electoral outcomes, urbanization has recently been considered a competing factor that might weaken the effects of ethnicity. Using a new methodology to model the compositional effects of ethnicity, we analyse the effects of both factors on the GE14 in our regression models. The findings show that both ethnicity and urban development do affect electoral outcomes, with ethnicity being the more dominant factor. Additionally, multivariate results show that neither malapportionment nor redelineation explains electoral outcomes. We provide a dissection of the 'Malaysian tsunami' examining vote change patterns between GE13 and GE14 using an ethnic and rural-urban continuum. The analysis reveals that effects of the tsunami are not evenly spread across ethnic groups and geographical regions, with the Malay majority and ethnically mixed seats displaying contrasting voting patterns. [ABSTRACT FROM AUTHOR]