Question

We have five samples of data: sample A with 30 successes of 50 cases, sample B with 600 successes of 1000 cases, sample C with 3000 successes of 5000 cases, sample D with 60 successes of 100 cases and sample E with 300 successes of 500 cases. We want to test if the proportion of successes is greater than 0.5. Which sample gives the strongest evidence for the alternative hypothesis?A. AB. BC. CD. DE. E

Answer 1

C. with 3000 successes of 5000 cases sample

Explanation:

Given that we need to test if the proportion of success is greater than 0.5.

From the given options, we can see that they all have the same proportion which equals to;

Proportion p = 30/50 = 600/1000 = 0.6

p = 0.6

But we can notice that the number of samples in each case is different.

Test statistic z score can be calculated with the formula below;

z = (p^−po)/√{po(1−po)/n}

Where,

z= Test statistics

n = Sample size

po = Null hypothesized value

p^ = Observed proportion

Since all other variables are the same for all the cases except sample size, from the formula for the test statistics we can see that the higher the value of sample size (n) the higher the test statistics (z) and the highest z gives the strongest evidence for the alternative hypothesis. So the option with the highest sample size gives the strongest evidence for the alternative hypothesis.

Therefore, option C with sample size 5000 and proportion 0.6 has the highest sample size. Hence, option C gives the strongest evidence for the alternative hypothesis