Dummy and Ordinal Dependent Variables

Stephen Bazen

in Econometric Methods for Labour Economics

Published in print September 2011 | ISBN: 9780199576791
Published online January 2012 | e-ISBN: 9780191731136 | DOI:

Series: Practical Econometrics

Dummy and Ordinal Dependent Variables

More Like This

Show all results sharing this subject:

  • Econometrics and Mathematical Economics


Show Summary Details


In many situations, the question addressed in labour economics is of a binary nature. An individual decides whether to participate or not in the labour force. He or she is either in or out. Sometimes, due to the way in which a survey is undertaken, data are only available for discrete binary outcomes — we do not know how many hours a person works, but we know that it is either part-time or full-time. In these circumstances, the variable that is being modelled is dichotomous and it is customary to treat such a variable as a dummy variable, sometimes referred to as a ‘(0,1)-dummy’ or an indicator variable. In terms of the notation for the dependent variable (yi) of the previous chapters, for each individual in the sample either yi = 0 or yi = 1. This type of data has given rise to the use of logit and probit models due to the discrete nature of the dependent variable. These are both nonlinear models and are estimated using maximum likelihood methods rather than by least squares. This chapter compares the results obtained by least squares and the logit/probit methods. It also examines how these methods can be adapted for use with more than two alternatives. In the latter context, there is an important distinction to be made between ordered alternatives and straightforward, non-hierarchical multinomial outcomes.

Keywords: logit models; probit modeks; nonlinear models; labour economics

Chapter.  10493 words.  Illustrated.

Subjects: Econometrics and Mathematical Economics

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.