where? I saw people who have to use traditional regression for binary
所有跟贴·加跟贴·新语丝读书论坛
送交者: mangolasi 于 2007-04-18, 16:26:18:
回答: Traditional regression does not make any sense in this case 由 HunHunSheng 于 2007-04-18, 16:22:42:
dependent variable because they use synthetic/aggregated data, and in that case simply b/c E(f(x)) != f(E(x)) for nonlinear f(x), they can no longer logistic/probit regression. Linear regression can perserve the nice property of aggregation.
所有跟贴:
加跟贴