Reporting of Trial Results Flashcards
What is the CONSORT statement?
A statement to improve the quality of reporting of RCTs
List the stages of the CONSORT diagram
Enrolment
Allocation
Follow-up
Analysis
What is entailed in the enrolment stage of CONSORT diagram?
External validity
What is entailed in the allocation stage of CONSORT diagram?
Internal validity - the extent to which a trial goes to eliminate
What is a p-value?
p-value is the probability (ranging from 0 to 1) that the results observed in a trial (or results more extreme) could have occurred by chance if the null hypothesis is true. Therefore, the smaller the p-value, the less likely the null hypothesis is to be true. For example, a p-value=0.0001 indicates the null hypothesis is very unlikely to be true whereas a p-value=0.53 indicates the observed results could easily have arisen by chance.
What is a confidence interval?
A confidence interval is an interval, constructed around an estimate from a sample (e.g. the estimate of the size of effect of an intervention), that indicates the uncertainty in the estimate because it was obtained from a sample.
Why is it important to consider both the p-value and confidence interval in the assessment of data?
A CI that is inclusive of 0 makes the assertion of the analysis invalid
What is a Kaplan-Meier Plot?
Key components for reporting results when the outcome for comparing treatment is the time for some disease/event to occur.
What additional information can be supplied alongside the KM plot to add to the information being given?
Median follow-up times
CIs or standard error
Add p-values to show statistical significance
How can we display potential publication bias graphically?
Funnel plots.
What is a funnel plot?
A graph that plots estimated treatment effect of a trial against its sample size /standard error.
How do funnel plots show potential publication bias?
Absence of smaller trials favouring against the intervention arm (negative trials) and an abundance of positive trials