An example: Ordinal Probit Model

We describe an ordinal Probit model for post-secondary education choice and estiamted a simple model with the dependant variable of interest is PSECHOICE and the explanatory variable is GRADES(Lower numberical value of GRADES indicate better performance). We rank the college possibilities as follows:
The following table shows the ordered Probit estimation results:

1. Based on the estimated results in the above table, comment on the changes for probabilities of “2-year college” group and “no college” group when GRADES increases. Explain if they are consistent with your expectations.
   Answer: when grades increases, the pr of the highest ranked choice (4-year) goes down, and the lowest ranked choice (no college)goes up, but difficult to say about 2 year college according to the formula of group 2. (According to marginal effect formula for group 1, we find that only sign of beta matter since the pdf is alwyas positive. These are consistent with the expectation.)
2. Compute the marginal effect of GRADES on the probability that a student with GRADES = 6 attends 2- year college.
   For Ordered Probit model,
   $$\frac{\partial P}{\partial x}$$