Presenting clinical trials data

Question 1

Confidence interval

Answer 1

A confidence interval gives an estimated range of values which is likely to include an unknown population parameter, the estimated range being calculated from a given set of sample data.

Question 2

why are confidence intervals more informative than the simple results of hypothesis tests

Answer 2

since they provide a range of plausible values for the unknown parameter.

Question 3

what is the point estimate

Answer 3

(usually the mean) indicates the magnitude of the effect of the experimental intervention compared to the control intervention (Risk ratio is 0.7 of that in the control group).

Question 4

what does the confidence interval describe

Answer 4

the uncertainty of the point estimate

Question 5

what does the confidence interval describe

Answer 5

range of values within which we can be reasonably sure that the true effect actually lies.

Question 6

narrow confidence intervals

Answer 6

there is a HIGHER level of confidence int he results

Question 7

wide confidence intervals

Answer 7

means there is LOWER confidence in the results

Question 8

why are confidence intervals better than p values

Answer 8

1. Give a range of possible effect sizes
2. Embrace the value of no difference between treatments (not significantly different from the control)
3. Help interpret clinical trial data by placing upper and lower bounds on the true effect size
4. Statistically significant does not mean clinically important –the size of the effect determines importance!

Question 9

Measuring the effectiveness of interventions

Answer 9

1. Number needed to treat
2. Relative risk
3. Odds ratio

Question 10

what is NNT (number needed to treat) a measure of the effectiveness of interventions

Answer 10

the difference between treatment and control in achieving a particular clinical outcome and is TREATMENT specific

Question 11

relative risk =

Answer 11

probability of getting disease if exposed / probability of getting disease if not exposed

Question 12

relative risk of a drug =

Answer 12

probability of outcome if on drug / probability of outcome if on placebo

Question 13

odds ratio =

Answer 13

odds that the disease was exposed / odds the control were exposed

Question 14

when would you use relative risk

Answer 14

cohort studies and clinical trials

Question 15

when would you use odds ratio

Answer 15

case-control studies

Question 16

Heterogeneity

Answer 16

this is the extent to which outcomes vary
• Clinical baseline
• Design related
• Statistical heterogeneity

Question 17

what is I squared in heterogeneity

Answer 17

the amount of variation not caused by sampling error