June 2019 Paper 1 Q11
11 It is known that, under the standard treatment for a certain disease, 9.7% of patients with the disease experience side effects within one year.
In a trial of a new treatment, a random sample of 450 patients with this disease was selected and the number \(X\) who experienced side effects within one year was noted.
It was found that 51 of the 450 patients experienced side effects within one year.
| Scheme | Marks | AO |
|---|---|---|
| e.g. The probability of side effects is the same for each patient (or is constant) e.g. The patients (or cases) are independent oe e.g. Patients form random sample of the population | B1 | 1.2 |
| [1] |
Notes
oe, in context. Allow any indication of context, eg "patient" or "side effects"
NOT Prob of patients getting side effects is indep or random.
Ignore all else
| Scheme | Marks | AO |
|---|---|---|
| See exemplars at end (below). Allow 2 sf throughout | ||
| \(\mathrm{H}_0: p = 0.097\) where \(p\) is the proportion of patients experiencing side-effects (within a year) or 9.7% of patients experience side-effects | B1 | 1.1 |
| \(\mathrm{H}_1: p \gt 0.097\) or \(\gt\) 9.7% exp side-effects | B1 | 2.5 |
| \(\mathrm{B}(450, 0.097)\) & \(X = 50\) (allow 51) | M1 | 3.3 |
| \(\mathrm{P}(X \geqslant 51) = 1 - 0.862 = 0.138\) (3 sf) | A1 | 3.4 |
| Compare 0.1 | A1f | 1.1 |
| Insufficient evidence to reject \(\mathrm{H}_0\) Allow "Not reject \(\mathrm{H}_0\)" Allow Accept \(\mathrm{H}_0\) | M1 | 1.1 |
| No evidence (at 10% level) that proportion experiencing side-effects in one year under new treatment is greater than under standard treatment | A1f | 2.2b |
| [7] |
Notes
B1: Allow "possibility" or, "probability". Not \(p\) = percentage having disease
B1: One error, eg undefined \(p\), \(p = 9.7\%\) B1B0
M1: stated or implied eg by 0.138 or 0.107 or 0.108 or 0.862 or 0.893 or 0.0308 or 0.0366
NB 0.138 seen (or 0.107 or 0.108 or 0.862 or 0.893) implies M1 even if part of incorrect statement, eg \(\mathrm{P}(X \leqslant 51) = 0.107\) or \(\mathrm{P}(X \gt 51) = 0.138\)
A1: cao BC
A1f: Dep 0.138 or 0.107 or 0.108 only
M1: Must see this statement oe. Dep 0.138 or 0.107 or 0.108 or \(\mathrm{P}(X \geqslant 51 \text{ or } 50)\) stated
Condone "Reject \(\mathrm{H}_1\)". Might be implied by conclusion. NB possible opposite conclusion on ft
A1f: Any equivalent statement, in context, not definite, eg allow "likelihood", "percentage". Ignore all else
ft only their \(\mathrm{P}(X \geqslant 51)\) and NB possible opposite conclusion on ft
NOT eg "change". NOT "proportion experiencing side effects is not significantly greater"
Context can be implied by, eg, "patients", "proportion"
0.108 seen: max B1B1M1A0A1M1A1
Bin(450, 0.1) used: max B1B1M0A0A0M1A1
If 2-tail test
| Scheme | Marks |
|---|---|
| \(\mathrm{H}_0: p = 0.097\) (defined \(p\)) | B1 |
| \(\mathrm{H}_1: p \neq 0.097\) | B0 |
| M1 | |
| A1 | |
| Comp 0.05 | A1 |
| No more marks |
Appendix
Qu 11(b) Examplar solutions
| Response | Marks |
|---|---|
| A \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) | B1B0 |
| \(\mathrm{P}(X \geqslant 51) = 0.138\) | M1A1 |
| \(0.138 \gt 0.1\) | A1 |
| Reject \(\mathrm{H}_1\) | M1A0 |
| B \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) where \(p\) = %age exp'ng side effects | B1B0 |
| \(\mathrm{P}(X \geqslant 51) = 0.107\) | M1A0 |
| \(0.107 \gt 0.1\) | A1 |
| Not reject \(\mathrm{H}_0\) | M1A0 |
| C \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) where \(p\) = proportion exp'ng side effects | B1B1 |
| Bin(450, 0.097) \(\mathrm{P}(X \leqslant 51) = 0.138\) | M1A1 |
| \(0.138 \gt 0.1\) | A1 |
| Not reject \(\mathrm{H}_0\) | M1 |
| Under new treatment there is not a greater prop exp side effects | A0 |
| D \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) where \(p\) = P(a patient exp side effects) | B1B1 |
| \(\mathrm{P}(X \leqslant 51) = 0.108\) | M1A0 |
| \(0.108 \gt 0.1\) | A1 |
| Not reject \(\mathrm{H}_0\) | M1 |
| There is not enough evidence that the alternative hypothesis is correct (No context) | A0 |
| E Let \(p\) be the probability \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) | B1B0 |
| Bin(51, 0.097) Ignore because next line is correct \(\mathrm{P}(X \leqslant 51) = 0.138\) | M1A1 |
| \(0.138 \gt 0.1\) | A1 |
| Not reject \(\mathrm{H}_0\) | M1 |
| Under new treatment there is not a greater prop exp side effects | A0 |
| F \(\mathrm{H}_0 = 0.097\) \(\mathrm{H}_1 \gt 0.097\) | B0B0 |
| Bin(450, 0.1) \(\mathrm{P}(X \geqslant 51) = 0.192\) | M0A0 |
| \(0.192 \gt 0.1\) | A0 |
| Reject \(\mathrm{H}_1\) | M1 |
| Insuff evidence that under new treatment there is a greater prop exp side effects | A1 |
| G \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) where \(p\) = P(a patient exp side effects) | B1B1 |
| Bin(450, 0.097), \(X = 51\) or \(X = 50\) | M1 |
| \(p = 0.0308\) | A0 |
| \(0.0308 \lt 0.1\) | A0 |
| Reject \(\mathrm{H}_0\) | M0 |
| There is evidence that under new treatment there is a greater prop exp side effects | A0 |
| H \(\mathrm{H}_0\): \(p(X = 0.097)\) \(\mathrm{H}_1\): \(p(X \gt 0.097)\) | B0B0 |
| \(\mathrm{P}(X \geqslant 51) = 0.0308\) | M1A0 |
| \(0.0308 \lt 0.1\) | A0 |
| Reject \(\mathrm{H}_0\) | M1 |
| There is enough evidence that a greater prop exp side effects | A1f |
| I \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) | B1B0 |
| \(p = 0.138\) | M1A1 A0 |
| Reject \(\mathrm{H}_1\) | M1 A0 |
| J \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) | B1B0 |
| \(X \sim \mathrm{Bin}(450, 0.097)\) \(p = 0.893\) | M1A0 |
| \(0.893 \gt 0.1\) | A0 |
| Not reject \(\mathrm{H}_0\) | M0 A0 |
| K \(\mathrm{H}_0: p = 0.097\) \(\mathrm{H}_1: p \gt 0.097\) \(p\) is the likelihood of a patient exp side effects | B1B1 |
| \(\mathrm{P}(X \geqslant 51) = 0.893\) | M1A0 |
| \(0.893 \gt 0.1\) | A0 |
| Not reject \(\mathrm{H}_0\) | M1 |
| No reason to think proportion decreased | A1 |
| L \(\mathrm{H}_0: p = 0.97\) \(\mathrm{H}_1: p = 0.97\) | B0B0 |
| \(\mathrm{P}(X \geqslant 50) = 0.0366\) | M1A0 |
| \(0.0366 \lt 0.1\) | A0 |
| Reject \(\mathrm{H}_0\) There is evidence prop has increased | M1A1f |