O'Reilly logo

Panel Data Econometrics with R by Giovanni Millo, Yves Croissant

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Chapter 9Count Data and Limited Dependent Variables

It is often the case in economics that the dependent variable is not continuous so that OLS estimation is not appropriate. On the one hand, the response may be a count, i.e., it takes only non‐negative integer values. In this case, the most commonly used specifications are the Poisson and the NegBin models. On the other hand, the response may exhibit limited dependence. In this case, one can assume that there exists a continuous non‐observable variable called images. The value of images is not observed for some part of the domain or not observed at all. The different cases are depicted in Figure 9.1:

  • Figure 9.1a presents the case of a binomial variable (images), which indicates the position of images relative to a threshold images,
  • Figure 9.1b presents the case of an ordinal variable (images), which indicates the position of relative to two thresholds and ,
  • Figure 9.1c presents ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required