In this paper, we examine the determinants of low-wage employment in Portugal. For this purpose, we use a data file of the European Community Household Panel (ECHP) for the years 1998 and 1999. In order to take into account unobserved heterogeneity in the data, a random-parameter logit model is used to analyse the probability of a worker receiving a low wage. The results indicate that the consideration that the effects of the explanatory variables are the same across all individuals, such as is assumed in most of the literature may be misleading. From the policy perspective, this implies that the use of a single instrument in order to combat low-wage employment is inappropriate to satisfy the whole population. In view of this, policies tailored by clusters would be more appropriate.