Lately many scholars pay particular attention to probit models considering different facets of this issue. Though this model was introduced quite recently, in 1980s, many works, estimating it from different angles, exist. In spite of numerous researches of the probit model many scholars contribute to its further considering, bringing about new issues in this connection.
For instance, Wooldridge (2009) suggests that probit model can be helpful in evaluating the impact of “certain policies in the context of a natural experiment”, concluding that such models can be used with panel data (Wooldridge, 2009, p. 587). He uses the standard approaches in considering this model, enwidening the understanding of the notion and suggesting possible areas to implement the probit model.
Ai and Norton (2003) argue that standard study of probit models is to be further considered, since there exist a lot of errors in this field; they also present “the correct way to estimate the magnitude” of the “interaction effect” in probit models (Ai and Norton, 2003, p.123). Their work provides thorough analysis of the existing model estimations, highlighting major discrepancies, and, finally, suggest their calculations in this connection.
Smith and LeSage (2004) suggest the spatial dependency of probit models with individuals in different locations. It is necessary to mention that though there many other works dedicated to the probit model and its spatial dependency, this comprehensive work can be regarded as good basis for the latter works. Kim et al. (2003) consider “a multinomial” probit model in terms of choice of work trip means they apply the Bayesian approach, estimating different ways with reference to travel cost and the time value (Kim et al., 2003, p.353).
The survey resulted in the conclusion that travelers are likely to account on time rather than cost; and that auto costs rising is likely to enhance the use of buses more than the use of subways. Thus, in this research probit model is applied to the economic issues in transport, and contributes to the improving of the transport related economic studies. Brooks (2008) considers the relevance of probit models, and suggests the best implications of this model, comparing them to logit models and other nonlinear models. It is necessary to stress that this model can be used not only in economics but can be applied to other areas of life.
For instance, Geweke et al.(2003) suggest to apply a Bayesian approach to the considering the mortality in terms of non-stochastic selection of patients and hospitals. That research is highly valuable in terms of assessing quality of hospitals and discharge databases of patients. Thus, the researchers made a very significant conclusion that “ignoring nonrandom admission would lead to invalid inference on quality” (Geweke et al., 2003, p.1237). The survey uses the latest methods, like probit models, to estimate medicine quality, which proves the universal implementation of the model.
Thus, it is necessary to point out that probit model is being considered from different angles and applied to different areas of social life. Especially in the present times it is highly researched in terms of its nonlinear structure, and multiplicity of its effects. Many scholars pay a lot of attention to estimating this model, using different methods and approaches. Nevertheless, the probit model still needs further investigations, in order to obtain better understanding of possible ways of its implementation.
Reference
Ai, C., Norton, E.C. (2003). Interaction terms in logit and probit models. Economics Letters. 80 (1) p. 123-129.
Brooks, C. (2008). Introductory econometrics for finance. Cambridge: Cambridge University Press.
Geweke J, Gowrisankaran G, Town RJ. (2003). Bayesian Inference for Hospital Quality in a Selection Model. Econometrica (71) p. 1215-1238.
Kim, Y., Kim, T.Y., Heo, E. (2003). Bayesian estimation of multinomial probit models of work trip choice. Transportation. 30 (3) p. 351-365.
Smith, T. E. and J. P. LeSage. (2004). “A Bayesian Probit Model with Spatial Dependencies,” in James P. LeSage and R. Kelley Pace (eds.), Advances in Econometrics: Volume 18: Spatial and Spatiotemporal Econometrics, Elsevier Science. p.127–160.
Wooldridge, J.M. (2009). Introductory econometrics: a modern approach. Mason, OH: Cengage Learning.