Dummy variable models:

In  the linear regression models considered in  previous units so far we have assumed the explanatory variables (i.e., the Xs)  to be numerical or quantitative in nature. But this may not always be the case. There can be instances when  the explanatory variable(s) are qualitative in  nature. These qualitative variables are often called the dummy variables. The purpose of this unit is to consider the role of such qualitative explanatory  variables  in  the regression  analysis and also to show how  the use  of dummy  variables make the  linear regression models an extremely  flexible tool  for handling many interesting problems encountered in empirical studies.  

In  many  instances in  regression equations we have explanatory variables which are qualitative in  nature.  It  is difficult to quantify these qualitative variables as they at best  can  be  divided  into certain categories.  In  such  cases we  use dummy  variable model.

The dummy variable can affect the intercept or slope or both. Accordingly, we take intercept or slope dummies. Remember that dumpy variables are used, as are explanatory variables, on the basis of the logic we build up.  Thus behind  every regression model there is a theoretical basis.

Dummy  variables can be  used  in  seasonal analysis. It  also can be used  in  pooling cross-sectional and time series data.