Linked from

The 54 pages that link to Confidence interval, each with the reason it gives.

• Randomized controlled trialRelated: It conveys the precision and uncertainty of an estimated trial effect.

• Monte Carlo methodRelated: It expresses sampling uncertainty around a Monte Carlo estimate.

• Sampling distributionRelated: Confidence intervals use sampling distributions to quantify the uncertainty of an estimate.

• Normal distributionRelated: Normal quantiles set interval widths when estimates have approximately normal sampling distributions.

• Central limit theoremRelated: Normal approximations from the theorem underpin many large-sample confidence intervals.

• Likelihood functionRelated: Likelihood-based procedures can produce confidence intervals by identifying parameter values compatible with the data.

• Statistical powerRelated: Intervals show effect-size uncertainty and can be more informative than a power label alone.

• Statistical significanceRelated: Intervals show estimate precision that a significant-or-not label conceals.

• Intelligence quotientRelated: A test score is an estimate, so its precision is better represented by a range than a point alone.

• Regression analysisRelated: Regression intervals quantify uncertainty in estimated coefficients.

• A/B testingRelated: Intervals show the range of effect sizes compatible with the experiment's data and method.

• Null hypothesisRelated: Intervals show effect sizes compatible with data, adding information a reject-or-not decision can conceal.

• Effect sizeRelated: Intervals show the uncertainty around an estimated effect size.

• Sampling errorRelated: Its width reflects sampling uncertainty under the assumed model or design.

• Standard errorRelated: Many confidence-interval formulas use a standard error to set the interval’s width.

• StatisticsRelated: It expresses estimation uncertainty through a range with a precise long-run interpretation.

• PrevalenceRelated: It conveys sampling uncertainty around an estimated prevalence.

• Statistical hypothesis testingRelated: Intervals convey plausible parameter values and precision beyond a binary test decision.

• Excess mortalityRelated: Baseline models and incomplete death counts make excess-mortality estimates uncertain.

• Frequentist statisticsRelated: Its confidence level describes long-run coverage, not a probability distribution for the fixed parameter.

• Type I and type II errorsRelated: Confidence levels and two-sided tests are linked through their shared error rates.

• Margin of errorRelated: The margin of error is the distance from the estimate to either endpoint of a symmetric confidence interval.

• Vaccine efficacyRelated: It shows the precision of an efficacy estimate, which a single percentage cannot convey.

• BiostatisticsRelated: Intervals communicate estimate precision beyond a single biomedical point estimate.

• Student's t-testRelated: A t-based interval expresses plausible values for a mean or mean difference alongside a test.

• Null hypothesis significance testingRelated: Intervals add estimates of plausible effect sizes that a binary test omits.

• Overconfidence effectRelated: People's subjective ranges often fail to achieve their claimed coverage.

• Parameter (statistics)Related: It expresses parameter uncertainty with a range rather than one estimate.

• BiometricsRelated: Intervals express the uncertainty attached to biometric estimates.

• Chi-squared distributionRelated: For normal data, chi-squared quantiles produce confidence intervals for a population variance.

• Population parameterRelated: It reports uncertainty about a parameter estimate rather than only a single value.

• Sample size determinationRelated: A desired interval width supplies a direct precision target for sample planning.

• Correlation coefficientRelated: Intervals express uncertainty around estimated population correlations.

• Parametric statisticsRelated: Parametric uncertainty estimates use the fitted model's sampling behavior.

• Correlation function measurementRelated: Sampling uncertainty determines how precisely each estimated correlation is known.

• Family (statistics)Related: Its coverage depends on the assumed sampling family and parameterization.

• Leave-one-subject-out cross-validationRelated: Uncertainty should reflect variation across subjects, not merely variation across their observations.