A common form of sample selection is called incidental truncation. That is, we do not observe y (e.g. wage offer) because of the outcome of another variable s (e.g. in-labour-force). If s is a function only of the exogenous explanatory variables then
a. we have to correct the sample selection problem by Heckit.
b. the OLS is consistent and Heckit is not necessary.
c. we can use the OLS but the standard errors need to be corrected.
d. none of the above