rococo (version 1.1.7)

RococoTestResults-class: Class "RococoTestResults"

Description

S4 class for storing results of the robust rank correlation test

Objects

Objects of this class can be created by calling rococo.test.

Slots

The following slots are defined for RococoTestResults objects:

count:

number of times in which the test statistic for a random shuffle exceeded the test statistic of the true data; see rococo.test.

tnorm:

list identifying t-norm to use or two-argument function; see rococo. If one of the standard choices "min", "prod", or "lukasiewicz" has been used, the list has one component, name that contains the string identifying the t-norm. If a user-defined function has been used, the list has two components: name contains "user-defined t-norm" or the name attribute of the function object if available and def contains the function object itself.

input:

character string describing the input for which rococo.test has been called.

length:

number of samples for which rococo.test has been called.

p.value:

p-value of test.

p.value.approx:

p-value as based on a normal approximation of the null distribution.

r.values:

vector containing tolerance levels for the two inputs; see rococo.test or rococo.

numtests:

number of (random) shuffles performed by rococo.test.

exact:

logical indicating whether p-value has been computed exactly; see rococo.test.

similarity:

character (vector) identifying the similarity measure(s) used by rococo.test.

sample.gamma:

test statistic (robust gamma rank correlation coefficient) determined by rococo.test.

H0gamma.mu:

empirical mean of test statistic for random shuffles

H0gamma.sd:

empirical standard deviation of test statistic for random shuffles

perm.gamma:

in case rococo.test was called with storeValues=TRUE, this slot contains the vector of test statistics for random shuffles.

alternative:

alternative hypothesis used by rococo.test.

Methods

show

signature(object = "RococoTestResults"): d displays the most important information stored in object

References

http://www.bioinf.jku.at/software/rococo/

U. Bodenhofer, M. Krone, and F. Klawonn (2013). Testing noisy numerical data for monotonic association. Inform. Sci. 245:21-37. DOI: 10.1016/j.ins.2012.11.026.

U. Bodenhofer and F. Klawonn (2008). Robust rank correlation coefficients on the basis of fuzzy orderings: initial steps. Mathware Soft Comput. 15(1):5-20.

See Also

rococo.test, rococo, show-methods

Examples

# NOT RUN {
## create data
f <- function(x) ifelse(x > 0.9, x - 0.9, ifelse(x < -0.9, x + 0.9, 0))
x <- rnorm(25)
y <- f(x) + rnorm(25, sd=0.1)

## perform correlation tests
ret <- rococo.test(x, y, similarity="classical", alternative="greater")
show(ret)

ret <- rococo.test(x, y, similarity="linear", alternative="greater")
show(ret)

ret <- rococo.test(x, y, similarity=c("classical", "gauss"),
                   r=c(0, 0.1), alternative="greater",
                   numtests=10000)
show(ret)
# }