OurBigBook.comSite Source code

Grouped-binomial logistic regression

For independent grouped counts

Y_{i} \sim Bin (n_{i}, p_{i})

, grouped-binomial logistic regression specifies

lo g \frac{p _{i}}{1 - p _{i}} = x_{i}^{T} β .

Fitting the proportions

Y_{i} / n_{i}

with binomial weights

n_{i}

gives the same likelihood.

 Ancestors (7)

 Incoming links (1)

Solution