Learn more about the terminology used in the Ending the HIV Epidemic: A Plan for America initiative.
Relative Standard Error (RSE)
When the value of an indicator was estimated rather than measured directly, there is always possible error in the estimation based on variation that can occur by chance. This is called a standard error, and it is a measurement of the likely difference between the estimated value and the true value (directly measured value) for the population. Lower percentages are considered more reliable for general use.
Relative standard errors (RSEs) were calculated for estimates of incidence, prevalence, and percentages of persons living with diagnosed HIV infection and were used to determine the reliability of estimates. Estimates with a RSE of < 30% meet the standard of reliability and is displayed. Estimates with a RSE of 30%–50% meet a lower standard of reliability and is displayed but should be interpreted with caution. Estimates with a RSE of > 50% are statistically unreliable and not displayed.
On this site, estimates with a relative standard error (RSE) of ≥30% are represented in the following way:
- Estimates with an RSE of 30%-50% are marked with an asterisk "*", indicating that they should be used with caution.
- Estimates with an RSE>50% are not shown, and are replaced with the phrase “Data N/A due to high relative standard error.