The information provided on Home Health Compare enables the user to calculate confidence intervals for each reported measure.
Confidence intervals can be used to estimate the precision of the calculated rates for home health agencies. A confidence interval is the range of values within which the population value or rate is likely to fall given the information from an (observed) sample. A confidence interval is a statistical determination based on the degree of certainty associated with an estimated value.
Two elements play an important role in determining a confidence interval: sample size and the observed value from the sample. The smaller the sample size, the greater the difference in rates must be in order for that difference to be statistically meaningful. Conversely, the closer the observed rate is to either 10% or 90%, the smaller the difference in rates must be in order for that difference to be statistically meaningful.
As can be seen in the table of estimated difference values that follows, both sample size and observed value from the sample influence how large a difference is needed between 2 agencies to be significant. For example, for 2 agencies that have between 25-75 episodes of care, a difference of more than 8.3% would be needed if the observed rates were above 90% or less than 10%, but a difference of more than 13.9% between the 2 agencies would be needed if the observed rate is about 50%. In general, large differences between 2 or more home health agency rates may be significant, and small differences between 2 or more home health agencies are usually not significant.
As the number of episodes of care used to calculate home health agency rates increases, the reliability and stability of the estimates will also increase.