Confidence interval
In frequentist inference, a confidence interval (CI) determines lower and upper bounds likely to contain (in repeated sampling) the true value of an unknown statistical parameter, such as a population mean.
≈ 7 min read
Confidence interval. encyclopegia.org, snapshot enwiki-001376255302. /a/confidence-interval
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
In frequentist inference, a confidence interval (CI) determines lower and upper bounds likely to contain (in repeated sampling) the true value of an unknown statistical parameter, such as a population mean. Rather than reporting a single point estimate (e.g. "the average screen time is 3 hours per day"), a confidence interval provides an interval, such as from 2 hours to 4 hours.
A confidence interval is based on a pre-defined coverage probability, called confidence level, typically 95%. A 95% confidence level does not imply a 95% probability that the true parameter lies within a particular CI calculated from a sample (such interpretation would be associated with the credible interval in Bayesian inference).
The confidence level instead reflects the long-run performance of the method used to generate the interval. In other words, if the same sampling procedure were repeated 100 times from the same population, approximately 95 of the resulting intervals would be expected to contain the true population mean.
The frequentist approach sees the true population mean as a fixed unknown constant, while the confidence interval is calculated using data from a random sample. Because the sample is random, the interval endpoints are random variables.
P(u(X) The number \gamma , which is typically large (e.g. 0.95), is sometimes given in the form 1 - \alpha (or as a percentage 100\cdot(1 - \alpha)% ), where \alpha is a small positive number, often 0.05. It means that the interval (u(X), v(X)) has a probability \gamma of covering the value of \theta in repeated sampling.
Alternatively, some authors simply require that P(u(X) The confidence level can be described as "at least 100\gamma% ". When it is known that the coverage probability can be strictly larger than \gamma for some parameter values, the confidence interval is called conservative, i.e., it errs on the safe side.
In many applications, confidence intervals that have exactly the required confidence level are hard to construct, but approximate intervals can be computed. The rule for constructing the interval may be accepted if P(u(X) to an acceptable level of approximation. \frac{\bar{X} - \mu}{S / \sqrt{n}} where \mu and n are the population mean and the sample size, respectively. \begin{align} \bar{X} &= \frac{1}{n} \left(X_1 + \cdots + X_n\right), \\ S^2 &= \frac{1}{n-1}\sum_{i=1}^n \left(X_i - \bar{X}\right)^2. \end{align} Then the value T = \frac{\bar{X} - \mu}{S/\sqrt{n}} has a Student's t distribution with n - 1 degrees of freedom.
This value is useful because its distribution does not depend on the values of the unobservable parameters \mu and \sigma^2 ; i.e., it is a pivotal quantity. Suppose we wanted to calculate a 95% confidence interval for \mu.
First, let c be the 97.5th percentile of the distribution of T . Then there is a 2.5% chance that T will be less than -c and a 2.5% chance that it will be larger than +c (as the t distribution is symmetric about 0). In other words, P_T(-c \leq T \leq c) = 0.95.
Consequently, by replacing T with \frac{\bar{X} - \mu}{S/\sqrt{n}} and re-arranging terms, P_X {\left(\bar{X} - \frac{cS}{\sqrt{n}} \leq \mu \leq \bar{X} + \frac{cS}{\sqrt{n}}\right)} = 0.95 where P_X is the probability measure for the sample X_1, \ldots, X_n . It means that there is 95% probability with which this condition \bar{X} - \frac \leq \mu \leq \bar{X} + \frac occurs in repeated sampling.
After observing a sample, we find values \bar{x} for \bar{X} and s for S, from which we compute the below interval, and we say it is a 95% confidence interval for the mean. \left[\bar{x} - \frac{cs}{\sqrt{n}}, \bar{x} + \frac{cs}{\sqrt{n}}\right]. \bar{X} \pm \begin{cases} \dfrac {2} & \text{if } |X_1-X_2| A fiducial or objective Bayesian argument can be used to derive the interval estimate \bar{X} \pm \frac{1-|X_1-X_2|}{4}, which is also a 50% confidence procedure. Welch showed that the first confidence procedure dominates the second, according to desiderata from confidence interval theory; for every \theta_1\neq\theta , the probability that the first procedure contains \theta_1 is less than or equal to the probability that the second procedure contains \theta_1 .
The average width of the intervals from the first procedure is less than that of the second. Hence, the first procedure is preferred under classical confidence interval theory.
However, when |X_1-X_2| \geq 1/2 , intervals from the first procedure are guaranteed to contain the true value \theta : Therefore, the nominal 50% confidence coefficient is unrelated to the uncertainty we should have that a specific interval contains the true value. The second procedure does not have this property.
Moreover, when the first procedure generates a very short interval, this indicates that X_1,X_2 are very close together and hence only offer the information in a single data point. Yet the first interval will exclude almost all reasonable values of the parameter due to its short width. The second procedure does not have this property.
The two counter-intuitive properties of the first procedure – 100% coverage when X_1,X_2 are far apart and almost 0% coverage when X_1,X_2 are close together – balance out to yield 50% coverage on average. However, despite the first procedure being optimal, its intervals offer neither an assessment of the precision of the estimate nor an assessment of the uncertainty one should have that the interval contains the true value.
This example is used to argue against naïve interpretations of confidence intervals. If a confidence procedure is asserted to have properties beyond that of the nominal coverage (such as relation to precision, or a relationship with Bayesian inference), those properties must be proved; they do not follow from the fact that a procedure is a confidence procedure.
Steiger suggested a number of confidence procedures for common effect size measures in ANOVA. Morey et al. point out that several of these confidence procedures, including the one for ω 2 , have the property that as the F statistic becomes increasingly small—indicating misfit with all possible values of ω 2 —the confidence interval shrinks and can even contain only the single value ω 2 = 0; that is, the CI is infinitesimally narrow (this occurs when p\geq1-\alpha/2 for a 100(1-\alpha)\% CI).
This behavior is consistent with the relationship between the confidence procedure and significance testing: as F becomes so small that the group means are much closer together than we would expect by chance, a significance test might indicate rejection for most or all values of ω 2 . Hence the interval will be very narrow or even empty (or, by a convention suggested by Steiger, containing only 0).
However, this does not indicate that the estimate of ω 2 is very precise. In a sense, it indicates the opposite: that the trustworthiness of the results themselves may be in doubt. This is contrary to the common interpretation of confidence intervals that they reveal the precision of the estimate.
Text derived from https://en.wikipedia.org/w/index.php?oldid=1376255302 under CC BY-SA 4.0; modifications have been made.