use https://www3.nd.edu/~rwilliam/statafiles/logist.dta, clear logit grade gpa tuce i.psi, nolog * Replay the results, this time getting the exponentiated coefficients logit, or use https://www3.nd.edu/~rwilliam/statafiles/logist.dta, clear quietly logit grade gpa tuce i.psi margins, at(gpa = 3 psi = 0 tuce = 20) predict(xb) margins, at(gpa = 3 psi = 0 tuce = 20) margins, at(gpa = 3 psi = 1 tuce = 20) predict(xb) margins, at(gpa = 3 psi = 1 tuce = 20) margins, at(gpa = 4 psi = 0 tuce = 25) predict(xb) margins, at(gpa = 4 psi = 0 tuce = 25) margins, at(gpa = 4 psi = 1 tuce = 25) predict(xb) margins, at(gpa = 4 psi = 1 tuce = 25) quietly logit grade gpa tuce i.psi, nolog quietly margins psi, at(gpa = (2(.1)4) ) atmeans marginsplot, noci scheme(sj) quietly margins, dydx(psi) at(gpa = (2(.1)4) ) atmeans marginsplot, noci scheme(sj) quietly logit grade gpa tuce i.psi, nolog quietly margins r.psi, at(gpa = (2(.1)4) ) atmeans marginsplot, scheme(sj) logit grade, nolog display 1 / (1 + exp(--.6466272)) logit, or display .5238095/(1 + .5238095)