Objectives: What sort of people become social entrepreneurs, and in what way do they differ from business entrepreneurs? This question is important for policy because there has been a shift from direct to indirect delivery of many public services, requiring a professional approach to social enterprise. Yet we know little about who sets up social enterprises. Prior work: Much prior work on social entrepreneurs has been based on small and convenience samples, and this is true in the United Kingdom as elsewhere. An exception is work based on annual UK Global Entrepreneurship monitor (GEM) surveys (e.g. Levie et al., 2006). Approach: Defining and distinguishing business from social entrepreneurs is problematic. However, inclusion of items that measured the relative importance of economic, social and environmental goals in the 2009 UK GEM survey enables us to compare business and social entrepreneurs based on two different definitions: activity-based (setting up or running a new business or any kind of social, voluntary or community activity, venture or initiative) and goals-based (setting up or running a new organisation which has mainly economic goals versus mainly social goals). We use logistic multivariate regression techniques to identify differences between business and social entrepreneurs in demographic characteristics, effort, aspiration, use of resources, industry choice, location and organisational structure, identified from a representative sample of 30,000 adults interviewed in the United Kingdom in 2009. Results: The results show that the odds of an early-stage entrepreneur being a social rather than a business entrepreneur are reduced if they are male, from an ethnic minority, if they work 10 hours or more per week on the venture, and if they ever worked in their parents business, while they are increased if they have higher levels of education and if they are a settled in-migrant to their area. Implications: These results suggest that a high proportion of social enterprise founders are part-time founders. This could be a cause for concern for policy-makers keen to shift delivery of professional services from the public sector to a professional third sector. Future surveys could test if there is a hand-over of control from founders to full-time managers as social enterprises mature. Value: To our knowledge, this is the first time that large representative samples of business and social entrepreneurs have been compared using multivariate analysis. This type of research complements case-based research, enabling hypotheses raised by qualitative research to be tested on representative samples of a population.