Significance level compensation for multiple comparisons.

compensateAlpha compensates statistical significance level (alpha) for multiple comparisons/tests.

compensateAlpha(alpha, n, method = c("bonferroni", "sidak"),
    r = 0)

Arguments

alpha

significance level to be compensated
n

comparison count
method

compensation method, 'bonferroni' is more conservative, but does not assume independence of the tests, 'sidak' is more liberal and assumes independence of the tests
r

optional mean "correlation between the tests made", the extreme value of 0 leads to full compensation, the extreme value of 1 leads to no compensation (as all the tests are considered equal). See the SISA help for explanation.

Value

Compensated significance level. It equals alpha/n for the 'bonferroni' method, and 1-(1-alpha)^(1/n)) for the 'sidak' method.

References

SISA, http://www.quantitativeskills.com/sisa/calculations/bonhlp.htm

See also

compensatePValue, p.adjust

Examples

compensateAlpha(.05,2,method='sidak')
#> [1] 0.02532057