Methoden vergleichen

	Konfidenzintervall	Statistische Power und Stichprobengröße
Fachgebiet	Forschungsstatistik	Forschungsstatistik
Familie	Process / pipeline	Process / pipeline
Entstehungsjahr	1937	1988
Urheber	Jerzy Neyman	Jacob Cohen
Typ	Concept	Concept
Wegweisende Quelle	Neyman, J. (1937). Outline of a Theory of Statistical Estimation Based on the Classical Theory of Probability. Philosophical Transactions of the Royal Society, 236, 333–380.	Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences (2nd ed.). Lawrence Erlbaum Associates. ISBN: 0-8058-0283-5
Aliasnamen	CI, 95% CI, credible interval, interval estimate	power analysis, sample size calculation, 1 minus beta, sensitivity
Verwandt	4	4
Zusammenfassung	A confidence interval (CI) is a range of values, calculated from sample data, that likely contains the true population parameter. Introduced by Jerzy Neyman in 1937, it provides an interval estimate rather than a single point estimate, incorporating both the observed value and the uncertainty around it. The standard 95% confidence interval is a robust, intuitive alternative to p-values for communicating research results.	Statistical power is the probability of detecting a true effect if it exists (1 − β). Power analysis determines the sample size required to detect a hypothesized effect size with specified Type I error (α) and Type II error (β) rates. Introduced by Jacob Cohen (1988), power analysis is foundational to research design: underpowered studies produce inflated effect size estimates and are unlikely to replicate. The standard benchmark is 80% power (β = 0.20), though critical studies may require 90% power.