It is common to all types of longitudinal data that one observes some social unit from at least two points in time. With such data several opportunities for analysis arise that are not present in cross-sectional data, for example, to study change processes and to account for unobserved variables in a more robust manner. There are many types of longitudinal data. I review some recent advances in analyzing two types: event histories and panel data. In Part I of this article I focus on seven recent advances in analyzing event history data: (i) techniques for dealing with unobserved explanatory variables, (ii) peculiarities of various sampling frames, (iii) time-aggregation bias, (iv) discrete time methods, (v) estimation procedures such as those based on Cox's partial likelihood, (vi) local hazard-rate models, and (vii) continuous state space models. In Part II of the article I focus on recent advances in analyzing panel data, with an emphasis on how panel data allows one better to take account of unobserved variables in the types of static relationships usually estimated with cross-sectional data.


Article metrics loading...

Loading full text...

Full text loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error