Which is false?

multinomial logit takes both binary and interval data and produces probabilities of purchase and market share projections as functions of the marketing mix

if your discrete dependent variable is binary $($e$.$g$.$ yes or no$),$ a binary logistic regression model is an appropriate option

if your discrete dependent variable is multichotomous $($i$.$e$.,$ involves more than two options$)$ and your independent. variables are characteristics of choice options, you will need a discrete choice such as the multinomial logistic model

all of the above

none of the above