statsmodels.stats.oneway.confint_noncentrality#

statsmodels.stats.oneway.confint_noncentrality(f_stat, df, alpha=0.05, alternative='two-sided')[source]#

Confidence interval for noncentrality parameter in F-test

This does not yet handle non-negativity constraint on nc. Currently only two-sided alternative is supported.

Parameters:
f_statfloat

F-statistic for which the noncentrality parameter is inverted.

dftuple

degrees of freedom df = (df1, df2) where

  • df1 : numerator degrees of freedom, number of constraints

  • df2 : denominator degrees of freedom, df_resid

alphafloat, default 0.05

Significance level for the confidence interval.

alternative{“two-sided”}

Other alternatives have not been implemented.

Returns:
float

The end point of the confidence interval.

See also

confint_effectsize_oneway

Notes

The algorithm inverts the cdf of the noncentral F distribution with respect to the noncentrality parameters. See Steiger 2004 and references cited in it.

References

[1]

Steiger, James H. 2004. “Beyond the F Test: Effect Size Confidence Intervals and Tests of Close Fit in the Analysis of Variance and Contrast Analysis.” Psychological Methods 9 (2): 164-82. https://doi.org/10.1037/1082-989X.9.2.164.