Intention to Treat

Question 1

What is the intention to treat principle?

Answer 1

Participants must be counted in the groups to which they were initially assigned, regardless of whether they were compliant with the intervention.
Includes those who withdraw.

Question 2

Rationale behind intention to treat principle?

Answer 2

In an RCT one sets out to estimate broader effects of allocating intervention to a group and not the narrow effects of those who comply.
In reality, few people adhere to treatments strictly.

Question 3

What does intention to treat principle give us?

Answer 3

Conservative estimate of treatment effect compared with what would be expected in ideal world of full compliance

Question 4

Advantages of intention to treat principle

Answer 4

Makes results from RCT more generalisable and pragmatic

Question 5

When might intention to treat principle not be suitable?

Answer 5

RCTs where investigation is of biological effects of drugs

Question 6

Impact of ITT analysis in non inferiority trials?

Answer 6

Will favour equality due to dilution

Question 7

When is ITT difficult to interpret?

Answer 7

If number of crossovers are high

Question 8

Ways of dealing with missing data

Answer 8

Test the difference
Use available data
Imputation of data
Statistical methods

Question 9

What is test the difference?

Answer 9

Test for difference between drop out group and available subject group.
Baseline characteristics if comparable can substantiate loss without further adjustment

Question 10

Ways of using available data to deal with missing data

Answer 10

LOCF
Worst case scenario analysis

Question 11

What does LOCF stand for?

Answer 11

Last observation carried forward

Question 12

When is LOCF useful?

Answer 12

Only for longitudinal observations where continuous scales are used

Question 13

Disadvantages of LOCF

Answer 13

Many psychiatric diseases have natural course of remission - LOCF does not allow for this’
‘Too good’ for controls and ‘too stringent’ for patient group

Question 14

What is worst case scenario analysis?

Answer 14

Assumes that those lost to follow-up did not improve on trial intervention. Hence, data of treatment failure subjects used as proxy.

Question 15

When is worst case scenario analysis used?

Answer 15

As part of sensitivity analysis

Question 16

Types of imputations of data

Answer 16

Replacing missing values with mean of group
Hot deck imputation

Question 17

What are some statistical methods to make up for missing data?

Answer 17

Multiple regression
Growth curve analysis
Random effects modelling
Multiple imputation

Question 18

What is hot desk imputation?

Answer 18

Involves finding similar person among subjects and using that persons score

Question 19

What is multiple regression?

Answer 19

Used to predict missing values based on several other variables in data set

Question 20

What is growth curve analysis?

Answer 20

Line is fitted through existing data points for each subject. From 2 data points, we can derive parameters for straight line. For 3; quadratic curve. For 4; cubic curve.

Question 21

What is needed for growth curve analysis

Answer 21

At least 2 follow-up visits

Question 22

What is the definition of random effects modelling?

Answer 22

Derives from the fact that, when we usually fit a regression line to data, we assume that the parameters are fixed i.e. the same for all subjects
In random effects model, we allow them to differ for each person

Question 23

Who defined random effects modelling?

Answer 23

Streiner

Question 24

Implications of random effects modelling?

Answer 24

We do not expect curves for people who drop out to be same as for people who complete study

Question 25

What is multiple imputation?

Answer 25

Sophisticated and accurate methods which use maximum likelihood and Monte Carlo procedures.

Question 26

Recommendations if missing data are imputed?

Answer 26

Some sensitivity analysis is performed to ensure study conclusions are not misleading

Question 27

Alternatives to ITT

Answer 27

Per-protocol analysis
Treatment-received analysis

Question 28

What is per-protocol analysis?

Answer 28

Only patient who sufficiently complied with trials protocol are considered in final analysis.

Question 29

Another name for per-protocol analysis?

Answer 29

On treatment analysis

Question 30

Which types of RCTs use per-protocol analysis?

Answer 30

Biological explanatory RCTs
Secondary analysis in effectiveness trials

Question 31

What is treatment-received analysis?

Answer 31

Analyse subjects according to actual treatment received - not allocation made.

Question 32

Disadvantage of treatment-received analysis?

Answer 32

Effect of randomisation is compromised due to contamination of trial by one group of subjects moving to other group

Question 33

ITT is the norm except when?

Answer 33

Overwhelming justification of different analysis policy

Question 34

Advantages of ITT

Answer 34

Retains balance of prognostic factors arising from original random treatment allocation
Gives unbiased estimate of treatment effect
Admits non-compliance and protocol deviations, reflecting clinical life

Question 35

Limitations of ITT

Answer 35

Estimate of treatment effect is conservative
In equivalence trials, ITT will favour equality of treatment
Interpretation is difficult if large proportion of participants cross over to opposite treatment arms

Question 36

Why is estimate of treatment effect conservative in ITT?

Answer 36

Dilution effect of non-compliance

Question 37

Requirements for ideal ITT

Answer 37

Full compliance with randomised treatment
No missing responses
Follow-up of all participants