The objective of this paper is to analyse the influence of individual variables and some spatial mobility characteristics of regional labour markets on overeducation in Spain. To achieve this aim, we use microdata from the Spanish Budget Household Survey to estimate a probit model for the probability of overeducation while accounting for sample selection and the presence of data at different levels (individuals and territory). The obtained results permit us to conclude that the sizes of local labour markets and the possibility of extending the job search to other labour markets by commuting are relevant factors in explaining overeducation in the Spanish labour market. In spite of differences in labour market institutions, our results are very similar to those obtained for other countries, particularly when working with more recent data.