Lecture 7

Question 1

What is a statement of risk?

Answer 1

A statement about the dangers of something that can either be believed or disbelieved.

Question 2

What are important factors to be included in a risk/benefit experiment?

Answer 2

• Realistic time scale
• Statistically valid (clear outcome)
• Multiple tests and repeats
• A control group (while considering fairness)
• Minimal side effects
• Ethical
• Unbiased
• Representative

Question 3

Define relative risk (RR)

Answer 3

The increase in incidence of a disease in the exposed group compared to the non-exposed group, found by calculating ratio of the probabilities of an event occurring in the exposed group to that in the non-exposed group.

Question 4

What is the equation for relative risk?

Answer 4

RR = relative risk
p = probability

Question 5

What is the equation for absolute risk increase?

Answer 5

ARI = absolute risk increase
p = probability

Question 6

What is the equation for relative risk increase (RRI)?

Answer 6

RRI = relative risk increase
p = probability

Question 7

What is the equation for the number needed to harm (NNH)?

Answer 7

NNH = number needed to harm
ARI = absolute risk increase

Question 8

What are relative risk increase and number needed to harm measured in?

Answer 8

%

Question 9

Define relative risk of success (RR)

Answer 9

The ratio of the probabilities of a positive outcome in the treated group (i.e. reduced incidence) to that in the non-exposed group.

Question 10

What is the equation for the relative risk of success?

Answer 10

RR = relative risk
p = probability

Question 11

What is the equation for absolute risk reduction?

Answer 11

ARR = absolute risk reduction
p = probability

Question 12

What is the equation for relative risk reduction?

Answer 12

RRR = relative risk reduction
p = probability

Question 13

What is the equation for the number needed to treat?

Answer 13

NNT = number needed to treat
ARR = absolute risk reduction

Question 14

What method can be used to determine if a trial result is significant?

Answer 14

The null hypothesis can be tested against.

Question 15

What is the p-value of significance if we want to be 95% confident that a result is not due to chance?

Answer 15

p = 0.05 (a.k.a 5% probability that the result is due to chance)

Question 16

Define null hypothesis

Answer 16

The hypothesis that there is no change in the outcome of a trial for a treated group compared to a control group.

Question 17

Define standard error

Answer 17

A measure of the statistical accuracy of an estimate.

Question 18

For a graph (bar chart) of the recovery rate of a control group and a treated group, how can the significance of the treatment be determined?

Answer 18

The treatment is significant if error bars do not overlap.

Question 19

Define standard deviation

Answer 19

The square root of the variance.

Question 20

What is the equation for standard deviation?

Answer 20

s = standard deviation
N = number of measurements made
x = measurement
x̄ = mean measurement

Question 21

What is the equation for the standard error of the mean (SEM)?

Answer 21

SEM = standard error of the mean
s = standard deviation
N = number of measurements made

Question 22

What is the student’s t-test?

Answer 22

A useful measurement when comparing small samples of two distinct groups (test and control) to look for a significant difference.

Question 23

The student’s t-test is an _________ test when the two populations don’t depend on one another.

Answer 23

Unpaired

Question 24

What is a single-tailed test?

Answer 24

A test that is only concerned with the significance of one end of the data (so either greater than or less than a specific value).

Question 25

How is the student’s t-test carried out?

Answer 25

The ratio of the difference in mean values to the standard error of the difference is taken.

Question 26

What is the equation for the student t-test?

Answer 26

t = statistic value
x̄ = mean measurement
SE = standard error of the difference in the means
s = standard deviation
N = number of measurements made

Question 27

What is the equation for the degrees of freedom for an unpaired t-test?

Answer 27

DF = degrees of freedom
N = number of measurements made

Question 28

What is a paired t-test?

Answer 28

A t-test that is taken for a single sample (so measurements are taken before and after treatment). This means that each measurement is paired.

Question 29

What is the equation for the degrees of freedom of a paired student t-test?

Answer 29

DF = sample size - 1

Question 30

What is a chi-squared test?

Answer 30

A test used to determine the significance of the difference between a set of measured (observed) values and the matching expected values.

Question 31

What is the equation for the chi-squared test?

Answer 31

χ² = statistic value
O = observed value
E = expected value

Question 32

What is the equation for the degrees of freedom for the chi-squared test?

Answer 32

DF = degrees of freedom
N = sample size

Question 33

Define Quality-Adjusted Life Years (QALY)

Answer 33

An attempt to measure the benefit of a treatment in adding (quality of) life expected where each year following the treatment is given a weighting between 0 and 1 with 1 being perfect health and 0 being death. A sum of these years is taken.

Question 34

Define Incremental Cost-Effectiveness Ratio (ICER)

Answer 34

The cost of a treatment divided by the QALY.

Question 35

How much is a human year worth to the NHS in treatment costs?

Answer 35

The NHS will pay £30,000 per QALY (this can go higher for end-of-life drugs).