Logit analysis in a rotating panel context and an application to self-employment decisions

The authors derive a methodology for analyzing logit models in a rotating panel context. They then apply the technique to test two theories of why and when salaried workers enter the informal self-employed sector. In the traditional view, workers fired from formal jobs queue in the informal sector to reenter the formal sector. The authors argue that for many, self-employment is a desirable goal, but that credit constraints often dictate that they work in the formal sector until enough start-up capital is accumulated. They model the decision to move as a stopped Markov process in which, in each period, the worker compare accumulated savings with the target level for switching sector dictated by the forecasted stream of discounted utility arising from employment labor and capital in each sector. They test and find support for the model using the new logit methodology and rotating panel data from Mexico.