8.37 Consider the cumulative logit model, logit[P(Y 5 j)] = a}- + Bjx, not having pro portional odds form. a. With continuous x taking values over the real line, show that the model is improper in that cumulative probabilities are misordered for a range of x values. b. When x is a binary indicator, explain why the model is proper but requires constraints on (of + 1%) (as well as the usual ordering constraint on {aJ-}) and is then equivalent to the saturated model