Confidence intervals (Module 1)

Question 1

Interpret EGO in one sentence:

Answer 1

There is about 95% probability that the true of value of EGO in (the whole population from which the study participants were recruited) lies between __ and __

Question 2

Interpret CGO in one sentence:

Answer 2

There is about 95% probability that the true value of CGO in (the whole population from which the study participants were recruited) lies between __ and __

Question 3

Interpret the statistical significance of the confidence intervals for EGO and CGO when they do not overlap:

Answer 3

It is reasonable to assume that EGO and CGO are truly different from each other in the underlying population (insert eligibility criteria) rather than just due to random error. The confidence intervals for RR and RD will not cross the no-effect line and hence the study results are statistically significant.

Question 4

What are the key features of when the confidence intervals do NOT overlap in terms of statistical significance?

Answer 4

EGO is not the same as CGO
RR and RD confidence intervals will NOT cross the no-effect line
There is a real difference between EGO and CGO so the exposure factor has had an effect

Question 5

Interpret the statistical significance of the confidence intervals for EGO and CGO when they DO overlap:

Answer 5

We are unable to determine if EGO is different from CGO in the population from which the study participants were recruited (insert eligibility criteria). The confidence intervals for RR AND RD will usually cross the no-effect line. The study results are not significant as there is too much random error to determine if there is a real difference between EGO and CGO.