Last modified: 11/3/25

ANESTHESIOLOGY

Confidence Intervals

Confidence intervals (CI) are measures of uncertainty around effect estimates.

1,2,3

Frequentist confidence intervals are most commonly reported.

Interpretation: We can be 95%

confident that the true (unknown) estimate would lie within the lower and upper limits of the

interval, based on hypothesized repeats of the experiment.

For studies using Bayesian methods, report a credible interval.

Interpretation: There is a 95%

probability that the true (unknown) estimate would lie within the interval, given the evidence

provided by the observed data.

Confidence intervals containing zero for continuous measures or one for odds ratios or hazard

ratios are considered compatible with the lack of an effect or association, and the findings would

be interpreted as having negative or neutral results.

However, be careful to not only dichotomize a

CI interpretation into significant or not significant.

2,5

The width (precision) is also important to a

discussion of the values.

1,2,3,6

The CI width (degree of uncertainty) varies according to two factors:

1) sample size (n) - inversely proportional to the degree of uncertainty; the larger the sample

size, the smaller the CI width, which would indicate a lower degree of uncertainty.

2) study heterogeneity (standard deviation [SD] or standard error [SE]) - directly proportional

to the degree of uncertainty, the lower the heterogeneity the lower the uncertainty.

Common misinterpretations of confidence intervals:

• The specific 95% CI presented by a study has a 95% chance of containing the true effect size.

2,4

• An effect size outside the 95% CI has been refuted (or excluded) by the data.

• If two CIs overlap, the difference between two estimates is not significant.

• An observed 95% CI predicts that 95% of estimates from future studies will fall inside the

observed interval.

2,7

• If one 95% CI includes the null value and another excludes that value, the interval excluding the

null is the more precise one.

References

1. Freire A, Elkins MR, Ramos EMC, et al. Use of 95% confidence intervals in the reporting of

between-group differences in randomized controlled trials: analysis of a representative sample

Last modified: 11/3/25

of 200 physical therapy trials. Braz J Phys Ther. 2018;(October),

http://dx.doi.org/10.1016/j.bjpt.2018.10.004.2.

2. Sim J, Reid N. Statistical inference by confidence intervals: issues of interpretation and

utilization. Phys Ther.1999;79(2):186---195.3.

3. Harrell F. Glossary of statistical terms. Published 2025. Accessed September 19, 2025.

https://hbiostat.org/glossary/

4. Lesaffre E, Lawson AB. Bayesian Biostatistics. Chichester: John Wiley & Sons, Ltd; 2012.4.

5. Amrhein V, Trafimow D, Greenland S. Inferential statistics as descriptive statistics: there is no

replication crisis if we don’t expect replication. Am Stat. 2019;73(Sup 1):262-270. doi:10.1080/

00031305.2018.1543137

6. McGlothlin AE, Lewis RJ. Minimal clinically important difference: defining what really matters to

patients. JAMA. 2014;312(13):1342-1343. doi:10.1001/jama.2014.13128

7. Goodman SN, Berlin JA. The use of predicted confidence intervals when planning experiments

and the misuse of power when interpreting results. Ann Intern Med. 1994;121(3):200-206.

doi:10.7326/ 0003-4819-121-3-199408010-00008

Additional information:

1. Bellhouse DR. The central limit theorem under simple random sampling. Am Stat.

2001;55(4):352---357.

2. Hoenig JM, Heisey DM. The abuse of power. Am Stat. 2001;55(1):19-24. doi:10.1198/

000313001300339897

3. Hung ML, Wu JX, Li N, Livhits MJ, Yeh MW. Association of radioactive iodine administration after

reoperation with outcomes among patients with recurrent or persistent papillary thyroid

cancer. JAMA Surg. 018;153(12):1098-1104. doi:10. 1001/jamasurg.2018.2659

4. Wilkinson M. Distinguishing between statistical significance and practical/clinical

meaningfulness using statistical inference. Sports Med. 2014;44(3):295---301.5.