consider simplified versions of the dependent variable as the number of locations in which the MNEs are present as well as the number of their subsidiaries.A large part of the empirical literature concerning the link between productivity and the scope and the scale of MNEs uses data of firms from a single country. Our paper uses a multi-country data set. We deliberately enlarge the number of countries to introduce more variability in the data, taking into consideration the control of the heterogeneity coming from the existence of parent multinationals from different countries. A second contribution of our paper is that we use count data models to estimate the scope elasticity. This is a statistical technique almost not used in this research area. Given that the dependent variable is the number of subsidiaries that the parent firm has in a foreign market, we think this technique is more appropriate for estimating the scope elasticity. Furthermore, we take into consideration the existence of a large number of zeros (no subsidiaries in a given foreign market). An appropriate approach to deal with this issue is to estimate zero-inflated versions of count models (Cameron & Trivedi, 2005). This alternative approach proves that there is a systematic bias when scope elasticities are estimated not taking this into account. Overall, our contribution in estimating scope and scale elasticities associated with the multinational activity of firms is, on the one hand, the use of a multi-country data set, which is relatively infrequent in the available empirical literature and, on the other hand, the use of new estimation procedures for scope elasticity, in particular.The third prediction coming out from the model of firm heterogeneity and multinational production refers, as we mentioned before, to the relationship between the attributes of the destination countries (distance, size of the country, etc.) that make FDI more or less attractive and the characteristics of the productivity distributions of firms entering foreign markets. There is an asymmetry between both elements: those country attributes that positively affect the entry of MNEs are negatively related to the average productivity of parent firms entering abroad, and the opposite for those country attributes that have a negative impact on FDI activity. We call this result the "asymmetric effect hypothesis." Although this is a central prediction of the model of firm heterogeneity and multinational activity, empirical evidence on this hypothesis is rather limited. To our knowledge, it has been considered by Yeaple (2009), Chen and Moore (2010) and Hyun and Hur (2013). The first paper examines a sample of US multinationals, the second contains an application for French multinationals and the third refers to South Korean firms.Concerning the asymmetric effect prediction, our contribution here is to provide additional evidence using a multi-country data set which is richer in terms of the variability of the country characteristics and also in the dispersion of the productiv...