Critical Numbers 1

Question 1

risk ratio =

Answer 1

A/B

Question 2

risk difference =

Answer 2

A - B

Question 3

NUMBER NEEDED TO TREAT

Answer 3

1/|RD|

Question 4

NUMBER NEEDED TO HARM

Answer 4

1/RD if RD > .0

Question 5

RELATIVE RISK DIFFERENCE

Answer 5

A - B/B x100%

Question 6

Pyramid of evidence

Answer 6

1. Systematic review/ Meta-analysis of RCTs
2. RCTs
3. Controlled cohort study
4. Case control study
5. Case series
6. Case study
7. Anecdote
8. Wishful thinking/blind hope/delusional thinking

Question 7

Confounding:

Answer 7

A factor that independently influeneces the outcome of a situation but doesn’t lie on the causal pathway

Question 8

2 approaches to stats:

Answer 8

Confidence Intervals

PI values

Question 9

If a CI goes over 0…

Answer 9

it is not statistically significant

Question 10

What is a confidence interval?

Answer 10

A range of values, so defined hat the true value probably lies within

Question 11

P values are always between…

Answer 11

0 and 1

Question 12

When your p value is small:

Answer 12

It is very unlikely that your results are down to chance.

Reject Ho

Question 13

When your p value is large:

Answer 13

It is likely that your results are down to chance

Accept/do not reject Ho

Question 14

P values are statistically significant if they are…

Answer 14

less than 0.05

Question 15

Cross-sectional studies:

Answer 15

Non-experimental
Observational
Individual based
Analytic

Question 16

Case-control study:

Answer 16

Non-experimental
Observational
Individual based
Analytic

Question 17

Cohort-study:

Answer 17

Non-experimental
Observational
Individual based
Analytic

Question 18

Ecological study:

Answer 18

Non-experimental
Observational
Population based
Analytic

Question 19

Descriptive study (health survey):

Answer 19

Non experimental
Observational
Population based
Descriptive

Question 20

Case reports/series:

Answer 20

Non experimental
Observational
Individual based
Descriptive

Question 21

RCT:

Answer 21

Experimental
Interventional study
Randomized

Question 22

Quasi-experimental/ Field trial/ Community trial:

Answer 22

Experimental
Interventional study
Non-randomized

Question 23

RCT strengths:

Answer 23

Minimise bias and confounding
Can look at multiple outcomes
Strong evidence of causal relationship

Question 24

RCT weaknesses:

Answer 24

Huge cost
Huge teams
Dropouts
Ethical concerns
Complex to manage

Question 25

What does a case-control study do?

Answer 25

Looks at individual cases, past exposure is measured, prevalence of past exposure among cases and controls are compared.

Question 26

What does a cross-sectional study do?

Answer 26

Measures outcomes and exposure variables simultaneously in a given population at a given time

Question 27

What does an observational study do?

Answer 27

Record outcomes without intervention

Question 28

What does PICO stand for?

Answer 28

Patient/population Intervention Comparison/Control Outcome

Question 29

What does PPI stand for?

Answer 29

Patient Public Involvement

Question 30

What does a descriptive study do?

Answer 30

Describes the occurrence of a disease, generates a hypothesis based on aetiology

Question 31

What is cluster sampling?

Answer 31

A population is partitioned into groups or clusters and a sample of clusters is selected by simple random sampling

Question 32

What is stratified random sampling?

Answer 32

A population is partitioned into groups and a sample is selected by simple random sampling in each group.

Question 33

What is systemic random sampling?

Answer 33

Members of the population are selected at equal intervals, first member is selected at random

Question 34

What is standard deviation?

Answer 34

A degree of variability around the mean value

Question 35

What is the clinical use of standard deviation?

Answer 35

The mean plus or minus two s.d. is considered the normal reference range. E.g. normal Hb levels

Question 36

When is standard error low?

Answer 36

When sample size is large and/or variability in the data is low

Question 37

Equation for standard error:

Answer 37

SE = SD/ square root n

Question 38

The width of a CI depends on:

Answer 38

SE | level of confidence

Question 39

The wider a CI..

Answer 39

the less precise