Topic 7: Analysis and Analysis Populations

Question 1

What tests/analysis methods do we use for comparing continuous data

Answer 1

T-test, linear regression

Question 2

What tests/analysis methods do we use when comparing categorical data

Answer 2

chi square test, logistic regression, ordinal logistic regression, multinomial logistic regression

Question 3

What tests/analysis methods do we use when comparing time to event data.

Answer 3

Kaplan Meir survival curve, log rank test, cox regression

Question 4

What are two reasons you can have censoring

Answer 4

The patient has withdrawn from the trial or reached the end of the trial without witnessing the event.

Question 5

What can you do if the assumptions of the analysis model are not met

Answer 5

Transformations, non-parametric methods

Question 6

What do most basic methods of analysis assume

Answer 6

The observations are independent.

Question 7

How is analysis done on paired data

Answer 7

Look at the difference between observations for each participant and the variability of differences, then do analysis on a single sample.

Question 8

How does the randomisation method affect the analysis

Answer 8

Any factors used in randomisation should be adjusted for in analysis.

Question 9

What happens if we don’t adjust for factors used in randomisation

Answer 9

We are ignoring the correlation between study groups that comes from balancing treatment groups using stratification. When the correlation is ignored, the standard errors of the treatment effect will be biased upwards, and we would say there is a bigger treatment effect than there actually is.

Question 10

How is adjusted analysis conducted

Answer 10

Through regression where we have covariates for things we want to adjust for.

Question 11

True/False: We should carry out statistical tests for differences between groups in terms of baseline characteristics

Answer 11

False - its not appropriate to do so

Question 12

In cluster randomised trials, what is the issue in terms of comparability

Answer 12

Comparability is not guaranteed when randomising small numbers of clusters.

Question 13

When should the analysis population be defined

Answer 13

Before analysis

Question 14

Give two ways to handle missing data that can arise through an intention to treat analysis population

Answer 14

Complete case population (only use participants for which we have no missing data) imputation of missing data (replacing with reasonable substitute values).

Question 15

What else do we need to clarify when saying we’re using per - protocol

Answer 15

What is counted as an adherence from protocol

Question 16

What is the safety analysis population usually

Answer 16

All randomised participants to any treatment. Usually defined as those who have received at least one dose of the treatment.

Question 17

What is a safety analysis population

Answer 17

Population of patients used to assess the safety of that treatment.

Question 18

Why is the safety analysis population usually done according to the treatment actually received

Answer 18

To give a true reflection of the safety of that treatment.

Question 19

What is the risk with using multiple subgroup analyses

Answer 19

Risk of false positive findings.

Question 20

What is the purpose of sensitivity analysis

Answer 20

Assess the robustness of findings and conclusions. Robust findings are those that are consistent with those from the primary analysis, even when the trial design has been changed slightly.

Question 21

What does sensitivity analysis assess the impact of

Answer 21

Impact or influence of key assumptions or variations on the overall conclusions.

Question 22

What kind of things might be changed in a sensitivity analysis

Answer 22

Methods of analysis, definitions of outcomes, protocol deviations, missing data, outliers.