EM optimization of latent-variable density models

There is currently considerable interest in developing general non-linear density models based on latent, or hidden, variables. Such models have the ability to discover the presence of a relatively small number of underlying `causes' which, acting in combination, give rise to the apparent complexity of the observed data set. Unfortunately, to train such models generally requires large computational effort. In this paper we introduce a novel latent variable algorithm which retains the general non-linear capabilities of previous models but which uses a training procedure based on the EM algorithm. We demonstrate the performance of the model on a toy problem and on data from flow diagnostics for a multi-phase oil pipeline.

The influence of socio-cultural environments on the performance of nascent entrepreneurs:an instrumental variable approach

The importance of informal institutions and in particular culture for entrepreneurship is a subject of ongoing interest. Past research has mostly concentrated on cross-national comparisons, cultural values, and the direct effects of culture on entrepreneurial behavior, but in the main found inconsistent results. The present research adds a fresh perspective to this research stream by turning attention to community-level culture and cultural norms. We hypothesize indirect effects of cultural norms on venture emergence. Specifically that community-level cultural norms (performance-based culture and socially-supportive institutional norms) impact important supply-side variables (entrepreneurial self-efficacy and entrepreneurial motivation) which in turn influence nascent entrepreneurs’ success in creating operational ventures (venture emergence). We test our predictions on a unique longitudinal data set (PSED II) tracking nascent entrepreneurs venture creation efforts over a 5 year time span and find evidence supporting them. Our research contributes to a more fine-grained understanding of how culture, in particular perceptions of community cultural norms, influences venture emergence. This research highlights the embeddedness of entrepreneurial behavior and its immediate antecedent beliefs in the local, community context.

Interest groups in multiple streams:specifying their involvement in the framework

Although interests inhabit a central place in the multiple streams framework (MSF), interest groups have played only a minor role in theoretical and empirical studies until now. In Kingdon’s original conception, organized interests are a key variable in the politics stream. Revisiting Kingdon’s concept with a particular focus on interest groups and their activities—in different streams and at various levels—in the policy process, we take this argument further. In particular, we argue that specifying groups’ roles in other streams adds value to the explanatory power of the framework. To do this, we look at how interest groups affect problems, policies, and politics. The influence of interest groups within the streams is explained by linking the MSF with literature on interest intermediation. We show that depending on the number of conditions and their activity level, interest groups can be involved in all three streams. We illustrate this in case studies reviewing labor market policies in Germany and chemicals regulation at the European level.