Question 4: For the odds ratio, the authors give 95% confidence interval 0.78 to 1.13. What does this mean and how does it help us to interpret the results of this study?
We are using the subjects in this study as a sample to estimate the odds ratio in the whole population from which they come. Some samples will give us estimates above the population odds ratio, others will give estimates below it. We estimate a range of values which we think should include the population value. This is called an interval estimate. A 95% confidence interval is chosen so that 95% of intervals from such samples will include the population odd ratio.
In this study, we estimate that the odds ratio in the population, and hence the relative risk, is between 0.78 and 1.13. We estimate that the risk of glioma is increased by at most a factor 1.13, or 13%.
Back to Exercise: Glioma and mobile phones.
To Clinical Biostatistics index.
To Martin Bland's M.Sc. index.
To Martin Bland's home page.
This page maintained by Martin Bland.
Last updated: 31 July, 2006.
Back to top.