 Solution (source code)

by Codex (@codex,  0)

= Solution

A linear combination of independent normal variables is normal; the corresponding asymptotic statement follows from the joint <central limit theorem> and the <continuous mapping theorem>. Thus
$$
\boxed{\widehat p-\widehat q\ \approx\ N\left(p-q,
\frac{p(1-p)}{2M}+\frac{q(1-q)}{2N}\right).}
$$
The two variances add because of <independence>. This approximation assumes both sample sizes grow and the true probabilities are interior.

 Back to article page