OwensQ: Owen's Q-function

In Detlew/PowerTOST: Power and Sample Size for (Bio)Equivalence Studies

Owen's Q-function

Description

Calculates Owen’s Q function.

Usage

OwensQ(nu, t, delta, a=0, b)

Arguments

nu	degree of Owen’s Q
t	parameter t
delta	parameter delta
a	lower integration limit, only a=0 implemented
b	upper integration limit

Details

Uses the relationship to non-central t-distribution (see Chou)

⁠ OwensQ = pt(t, df=nu, ncp=delta) - Integal_b_Inf(Q_integrand)⁠

The definite integral is numerically evaluated using integrate after a variables transformation resulting in the integration range from 0 to 1 instead of the semi-infinite original range. This may result in higher precision and better numerical stability.

The arguments to the function must be scalars. No vectors allowed.

Value

Numeric value of Owen’s Q-function at given input arguments.

Note

This function is intended for internal use in the power calculations.
But may be useful for others.

Author(s)

D. Labes

References

Owen DB. A special case of a bivariate non-central t-distribution. Biometrika. 1965;52(3/4):437–46. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.2307/2333696")}

Chou YM. A bivariate noncentral T-distibution with applications. Commun Stat Theory Methods. 1992;21(12):3427–62. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1080/03610929208830988")}

See Also

OwensQOwen

Examples

# This function is mainly intended for internal use.
OwensQ(10, 2.5, 5, 0, 2)
#should give [1] 9.388137e-06 
OwensQ(10, -2.5, -5, 0, 2)
#should give [1] 0.05264363 

Detlew/PowerTOST documentation built on March 26, 2024, 12:18 a.m.