There is a known connection between the multinomial and the Poisson likelihoods. This, in turn, means that a Poisson regression may be transformed into a logit model and vice versa. In this paper, I show the data transformations required to implement this transformation. Several examples are used as illustrations.
Từ khóa
Tài liệu tham khảo
10.2307/2348134
10.1162/003465303762687811
10.2307/1911191
Lang J., 1996, Journal of the Royal Statistical Society, 58, 253, 10.1111/j.2517-6161.1996.tb02079.x
