ABSTRACT
The starting point for any econometric analysis is the specification of an econometric model that describes the core economic relationship that is under examination. This chapter begins with an overview of the types of data that are used by applied health economists; a comprehensive understanding of the data that are available is a key requirement in specifying, estimating and interpreting an appropriate econometric model. It provides an overview of the types of econometric models that are typically employed by applied health economists, focusing on the techniques appropriate for the types of outcomes commonly used in applied health economics research. Non-linear relationships are a common feature of many applications in health economics. In general, non-linear econometric models are specified to explain limited dependent variables, that is, a variable whose range is restricted in some way. Count data typically contain a large proportion of zero observations, as well as a long right tail of observations.
