ortho: Test a matrix of contrast coefficients for pairwise...

In asuR: Advanced statistics using R

Description

This function tests all pairwise contrast coefficients for orthogonality. The function tells the user which pair of contrasts are not orthogonal.

Usage

ortho(contr, round = 10)

Arguments

contr	A matirx, wiht k-1 rows (one for each contrast) and k columns one for each level of a factor.
round	To test if the sum of the products of the coefficients is zero the sum is rounded using this value as digits argument for round.

Details

For all pairs of contrasts coefficients the sum of the products of the coefficients is calculated and compared if it is zero or not.

Value

a logical

Note

There are more elegant solutions to this problem but this one tells the user which pairs of contrasts are not orthogonal.

Author(s)

[e-mail]

References

none

See Also

mancontr

Examples

trt.contr <- rbind("control-sugar"=c(1, -1/4, -1/4, -1/4, -1/4),
                   "pure-mixed"=c(0, 1/3, 1/3, -1, 1/3),
                   "monosaccharides-disaccharides"=c(0,1/2,1/2,0,-1),
                   "gluc-fruc"=c(0,1,-1,0,0))
ortho(trt.contr)

asuR documentation built on May 2, 2019, 4:50 p.m.