The alternative hypothesis:

\(H_{0}: p_{1}-p_{2}>0\)

Here, from above hypothesis \(p_{1} — p_{2} = 0\) and we know that for a one-tailed hypothesis test with level of significance a, we reject \(H_{0}\) whenever the difference of proportions falls outside the \(c= 1-\alpha\) confidence interval for p based on the sample data. If a 98% confidence interval for \(p_{1} — p_{2}\) contains only positive numbers then we should reject \(H_{0}\ at\ \alpha = 0.02\) because the confidence interval does not contain 0. We know that 99% confidence interval is greater than 98% confidence interval and 99% confidence intervalmight contain 0. So, we don’t have enough evidence to reject null hypothesis \(H_{0}\ at\ \alpha = 0.01\) level of significance.