miChiSquareTest(x, df) miFTest(x, df1, df2)
miVariable
or
miList
object whose imputations are
scalar chi-square or F statistics.
df
or
df1
.
df2
).
Schafer, J. L. (1997).
Analysis of Incomplete Multivariate Data.
Chapman & Hall, London, page 115.
Li, Meng, Raghunathan and Rubin (1991).
Significance Levels from Repeated p-Values with Multiply-imputed Data.
Statistica Sinica
1, 65-92.
Hesterberg, T. (1998).
Combining multiple imputation t, chi-square, and F inferences.
Insightful Technical Report number 75.
m.barley <- barley.exposed w <- runif(length(barley.exposed)) < .1 m.barley[w] <- NA m.barley <- miVariable(m.barley, data.frame(matrix(rpois(4*sum(w), barley.exposed[w]+.1), sum(w), 4))) ml <- miApply(m.barley, loglin, margin = list(1:2, c(1, 3))) miChiSquareTest(miApply(ml, "[[", "pearson"), df = miApply(ml, "[[", "df")) fit <- miEval(lm(chol14~., data = cholesterolImpExample)) sumfit <- miEval(summary(fit)) fstat <- miEval(sumfit$fstatistic) miFTest(x = miEval(fstat["value"]), df1 = miEval(fstat["numdf"]), df2 = miEval(fstat["dendf"]))