ci_f_ncp: CI for the Non-Centrality Parameter of the F Distribution

In confintr: Confidence Intervals

CI for the Non-Centrality Parameter of the F Distribution

Description

Based on the inversion principle, parametric CIs for the non-centrality parameter (NCP) Delta of the F distribution are calculated. To keep the input interface simple, we do not provide bootstrap CIs here. A positive lower (1-alpha)*100%-confidence limit for the NCP goes hand-in-hand with a significant F test at level alpha. According to ?stats::pf, the results might be unreliable for very large F values.

Usage

ci_f_ncp(x, df1 = NULL, df2 = NULL, probs = c(0.025, 0.975))

Arguments

x	The result of stats::lm() or the F test statistic.
df1	The numerator degree of freedom (df), e.g. the number of parameters (including the intercept) of a linear regression. Only used if x is a test statistic.
df2	The denominator df, e.g. n - df1 - 1 in a linear regression. Only used if x is a test statistic.
probs	Lower and upper probabilities, by default c(0.025, 0.975).

Value

An object of class "cint" containing these components:

• parameter: Parameter specification.

• interval: CI for the parameter.

• estimate: Parameter estimate.

• probs: Lower and upper probabilities.

• type: Type of interval.

• info: Additional description.

References

Smithson, M. (2003). Confidence intervals. Series: Quantitative Applications in the Social Sciences. New York, NY: Sage Publications.

See Also

ci_rsquared.

Examples

fit <- stats::lm(Sepal.Length ~ ., data = iris)
ci_f_ncp(fit)
ci_f_ncp(fit, probs = c(0.05, 1))

confintr documentation built on April 16, 2023, 1:08 a.m.