Inference for Poisson parameters can often be based on connections with binomial and multinomial distributions. Show how to test H 0 : μ 1 =μ 2 for two populations based on independent Poisson counts...

Inference for Poisson parameters can often be based on connections with binomial and multinomial distributions. Show how to testH
₀: μ₁=μ₂ for two populations based on independent Poisson counts (y
₁,y
₂), using a corresponding test about a binomial parameter π. [/Hint:Condition onn=y
₁+y
₂ and identify π=μ₁/( μ₁+ μ₂).] How can one construct a confidence interval for μ₁/ μ₂ based on one for π?