5. The hazard ratio = 0·80 with 95% CI 0·66–0·98. The centre of this confidence interval would be 0.82. Why is the hazard ratio point estimate not in the centre of its confidence interval?
The hazard ratio and its confidence interval are calculated on the logarithmic scale.
We estimate the log hazard ratio and its standard error. From these we find a 95% confidence interval for the log hazard ratio by subtracting or adding 1.96 standard errors. At this point, the confidence interval is symmetrical around the point estimate. Finally, we antilog to get back to the ratio on the natural scale. This makes the lower limit closer to the estimate than is the upper limit.
Back to question.
Back to Clinical Biostatistics index.
To Martin Bland's home page.
This page maintained by Martin Bland.
Last updated: 31 July, 2006.
Back to top.