biotools (version 4.3)

mvpaircomp: Multivariate Pairwise Comparisons

Description

Performs pairwise comparisons of multivariate mean vectors of factor levels, overall or nested. The tests are run in the same spirt of summary.manova(), based on multivariate statistics such as Pillai's trace and Wilks' lambda, which can be applied to test multivariate contrasts.

Usage

mvpaircomp(model, factor1, nesting.factor = NULL,
   test = "Pillai", adjust = "none", SSPerror = NULL, DFerror = NULL)
# S3 method for mvpaircomp
print(x, ...)

Value

An object of class mvpaircomp, a list of

st

an array containing the summary of the multivariate tests.

SSPcontrast

an array containing p-dimensional square matrices of sum of squares and cross-products of the contrasts.

adjust

a character string indicating the p-value adjustment method used.

fac1

a character string indicating the factor being tested.

fac2

a character string indicating the nesting factor.

Arguments

model

a multivariate analysis of variance (MANOVA) model, fitted using lm() or manova(); an object of class "mlm".

factor1

a character string indicating a factor declared in the model, whose levels will be compared in pairs.

nesting.factor

optional; a character string indicating a factor also declared in model whose levels will nest the contrasts performed with factor1. factor1 and nesting.factor can have pretty much any form or relationship, that is, not necessarily nested one another.

test

a character string indicating the type of multivariate statistics to be calculated to perform the F-test approximation. Default is "Pillai". Other options are: "Wilks", "Hotelling-Lawley" and "Roy". But they use to give very close results.

adjust

a character string indicating the p-value adjustment method for multiple comparisons. Default is "none". See p.adjust

SSPerror

optional; a numeric matrix representing the residual sum of squares and cross-products, to be used to compute the multivariate statistics.

DFerror

optional; a numeric value representing the residual degrees of freedom, to be used to compute the multivariate statistics.

x

an object of class mvpaircomp.

...

further arguments.

Author

Anderson Rodrigo da Silva <[e-mail]>

References

Krzanowski, W. J. (1988) Principles of Multivariate Analysis. A User's Perspective. Oxford.

See Also

manova

Examples

# Example 1
data(maize)
M <- lm(cbind(NKPR, ED, CD, PH) ~ family + env, data = maize)
anova(M)  # MANOVA table
mvpaircomp(M, factor1 = "family", adjust = "bonferroni")

# Example 2 (with nesting factor)
# Data on producing plastic film from Krzanowski (1998, p. 381)
tear <- c(6.5, 6.2, 5.8, 6.5, 6.5, 6.9, 7.2, 6.9, 6.1, 6.3,
          6.7, 6.6, 7.2, 7.1, 6.8, 7.1, 7.0, 7.2, 7.5, 7.6)
gloss <- c(9.5, 9.9, 9.6, 9.6, 9.2, 9.1, 10.0, 9.9, 9.5, 9.4,
           9.1, 9.3, 8.3, 8.4, 8.5, 9.2, 8.8, 9.7, 10.1, 9.2)
opacity <- c(4.4, 6.4, 3.0, 4.1, 0.8, 5.7, 2.0, 3.9, 1.9, 5.7,
             2.8, 4.1, 3.8, 1.6, 3.4, 8.4, 5.2, 6.9, 2.7, 1.9)
Y <- cbind(tear, gloss, opacity)
rate     <- gl(2, 10, labels = c("Low", "High"))
additive <- gl(2, 5, length = 20, labels = c("Low", "High"))

fit <- manova(Y ~ rate * additive)
summary(fit, test = "Wilks")  # MANOVA table
mvpaircomp(fit, factor1 = "rate", nesting.factor = "additive", test = "Wilks")
mvpaircomp(fit, factor1 = "additive", nesting.factor = "rate", test = "Wilks")

# End (not run)