Hi All An index computed at each individual level (say respondent level in a survey) - is given by Index_1 = A.x + B.y + C.z where A, B and C are known constants and X & Y are continuous and Z is a binary (Yes, No) response. x,y, and z are independent of one another. Has anyone ever come across an index that is a mixture of a continuous and binary measures - any links to references? Just wanting to understand the pros and cons of such a measure and whether a robust variance estimate for such an index can be constructed. Comments welcome. regards Vince