S4 June 2009 Q3
3. Define, in terms of \(\mathrm{H}_0\) and/or \(\mathrm{H}_1\),
(a) the size of a hypothesis test, (1)
(b) the power of a hypothesis test. (1)
The probability of getting a head when a coin is tossed is denoted by \(p\).
This coin is tossed 12 times in order to test the hypotheses \(\mathrm{H}_0 : p = 0.5\) against \(\mathrm{H}_1 : p \neq 0.5\), using a 5% level of significance.
(c) Find the largest critical region for this test, such that the probability in each tail is less than 2.5%. (4)
(d) Given that \(p = 0.4\)
(i) find the probability of a type II error when using this test,
(ii) find the power of this test. (4)
(e) Suggest two ways in which the power of the test can be increased. (2)
| Scheme | Marks |
|---|---|
| Size is the probability of \(\mathrm{H}_0\) being rejected when it is in fact true. or \(\mathrm{P}(\text{reject }\mathrm{H}_0 / \mathrm{H}_0\text{ is true})\) oe | B1 |
| (1) |
| Scheme | Marks |
|---|---|
| The power of the test is the probability of rejecting \(\mathrm{H}_0\) when \(\mathrm{H}_1\) is true. or \(\mathrm{P}(\text{rejecting }\mathrm{H}_0/\mathrm{H}_1\text{ is true})\) / \(\mathrm{P}(\text{rejecting }\mathrm{H}_0/\mathrm{H}_0\text{ is false})\) oe | B1 |
| (1) |
| Scheme | Marks |
|---|---|
| \(X \sim \mathrm{B}(12, 0.5)\) | B1 |
| \(\mathrm{P}(X \leqslant 2) = 0.0193\) | M1 |
| \(\mathrm{P}(X \geqslant 10) = 0.0193\) | |
| \(\therefore\) critical region is \(\{X \leqslant 2 \cup X \geqslant 10\}\) | A1A1 |
| (4) |
| Scheme | Marks |
|---|---|
| (i) \(\mathrm{P}(\text{Type II error}) = \mathrm{P}(3 \leqslant X \leqslant 9 \mid p = 0.4)\) | M1 |
| \(= \mathrm{P}(X \leqslant 9) - \mathrm{P}(X \leqslant 2)\) \(= 0.9972 - 0.0834\) | M1dep |
| \(= 0.9138\) | A1 |
| (ii) Power \(= 1 - 0.9138\) \(= 0.0862\) | B1 ft |
| (4) |
Notes
(d) (i) first M1 for either correct area or follow through from their critical region
2nd M1 dependent on them having the first M1. for finding their area correctly
A1 cao
(ii) B1 follow through from their (i)
| Scheme | Marks |
|---|---|
| Increase the sample size | B1 |
| Increase the significance level/larger critical region | B1 |
| (2) | |
| (12 marks) |