Publications
Using logit on big data – From iterative methods to analytical solutions (GfK Verein Working Paper Series)
DownloadStoltenberg, B. (2016). Using logit on big data – From iterative methods to analytical solutions. GfK Verein Working Paper Series, 2016(3).
2016
Using logit on big data
Keywords: logit, analytical solution, (sign) restriction, household panel modeling, GfK-BrandSimulator
Abstract:
Numerical optimization for logit models is often time consuming, at least for big data. In this paper I combine several analytical approaches to solve logit models in a practical context including (sign) restrictions and constraints. The application to a household panel model compares the two approaches on several dimensions.
Authors
- Birgit Stoltenberg, Senior Researcher, NIM, birgit.stoltenberg@nim.org