Research Methodology 3: RCTs

Question 1

Define a RCT

Answer 1

RCT: a study in which participants are allocated randomly between an intervention
(e.g. treatment) and a control group (e.g. no treatment or standard treatment)

Question 2

why are trials conducted?

Answer 2

1. Safety
   • Ascertain the safe dose of a
   new drug.
2. Efficacy/ Effectiveness
   • Demonstrate efficacy of new
   drug

Question 3

why do we randomise ?

Answer 3

When looking at cause-effect relationships, randomisation allows all
random factors (confounders) apart from the proposed cause to be
held constant between groups.

Question 4

define confounder

Answer 4

A confounder is a variable that influences both the dependent
variable and independent variable causing a spurious association.

Question 5

what does randomisation do

Answer 5

• Randomisation ensures all potential confounding variables (known
and unknown) will be distributed by chance across all study groups

Question 6

Define equipoise

Answer 6

Clinical equipoise means that there is genuine uncertainty in the expert
medical community over whether one treatment will be more beneficial
than another.

Question 7

what makes a good RCT?

Answer 7

Internal validity – is the IV causing the DV in this study?

External validity – to what extent can these findings be generalised to
other people, situations and times?

Question 8

Define bias

Answer 8

In statistics - ‘a tendency of an estimate to deviate in one direction
from a true value’

Question 9

list 4 types of bias

Answer 9

selection
performance
attrition
observer/detection

Question 10

define selection bias

Answer 10

Systematic differences between baseline characteristics of groups that
are compared
Study sample does not represent target population

Question 11

define performance bias

Answer 11

Systematic differences between groups in the care that is provided, or in
exposure to factors other than the interventions of interest

Question 12

define attrition bias

Answer 12

Systematic differences between groups in withdrawals from a study
• Can cause systematic differences between groups – e.g. one
treatment has more side effects than another.

Question 13

define observer/detection bias

Answer 13

Outcome measure does not adequately capture outcome of interest
• Systematic differences between groups in how outcomes are determined
Not adequately capturing the outcome of interest

Question 14

Define intention to treat

Answer 14

– analysed in treatment group they were

randomised to, whatever happens later.

Question 15

Define on-treatment analysis or per protocol analysis

Answer 15

only analyse

patients who finish the treatment according to the study protocol.

Question 16

how many types of trials can you blind and describe who is blinded in each?

Answer 16

open: no one
single: patient is blinded
souble: pt and dr blinded
triple: pt/dr/investigators

Question 17

what is the significance level?

Answer 17

0.05

Question 18

what is the power of the study accepted at ?

Answer 18

80-90%

Question 19

If i observe a difference and there is one what is this?

Answer 19

well powered

Question 20

if i observe no difference and there isn’t one what is this ?

Answer 20

well designed

Question 21

what is a type 1 error

Answer 21

observe a diff but no diff

Question 22

what is a type 2 error

Answer 22

observe no diff but there is a diff

Question 23

define the p value

Answer 23

The P-value is the probability of observing the result you got, or more
extreme, if the null hypothesis were true,
where the result is a statistic estimated on the data you have collected in your
study.

Question 24

why do we calculate sample size?

Answer 24

Too few participants... If you get a null result, you don’t know
if you have:
• Evidence of no effect
• or simply…
• No evidence of an effect
too many = not ethical

Question 25

what does parametric data assume

Answer 25

normally distributed

Question 26

define positive and negative skew

Answer 26

look at the tables

Question 27

what do you use if your data is skewed? descriptive analysis

Answer 27

median and IQR

Question 28

if data is normally distributed which statistical tests would you use?

Answer 28

t test (scale)
chi sqaured (categories)
anova (scale)

Question 29

what assumptions are made for a t test

Answer 29

random sample
independent observation
normally distributed
variances for each group are equal

Question 30

what test is used if data is non-parametric

Answer 30

Mann-Whitney U/Wilcoxon Rank Sum replace t-test