Another model (Dobbie and Welsh 2001) for zero-inflated count data uses the Neyman type A distribution, which is a compound Poisson–Poisson mixture. For observation i, let zi denote a Poisson variate with expected value

????i. Conditional on zi, let wij (j = 1,…,zi) denote independent Poisson(????i)

observations. The model expresses yi using the decomposition yi = ∑zi j=0 wij, i = 1, 2,…, n. Find E(yi). Relating ????i and ????i to explanatory variables through log(????i) = x1i????1 and log(????i) = x2i????2, show the model for E(yi) and interpret its parameters.