independence.test {multivariance} | R Documentation |
This computes a test of independence for the columns of a sample matrix (required for the resampling test) or for given centered distance matrices (only possible for the distribution-free test).
independence.test(x, vec = 1:ncol(x), alpha = 0.05, type = "distribution_free", verbose = TRUE, ...)
x |
either a data matrix or a list of centered distance matrices |
vec |
if x is a matrix, then this indicates which columns are treated together as one sample; if x is a list, these are the indexes for which the multivariance is calculated. The default is all columns and all indexes, respectively. |
alpha |
significance level |
type |
one of |
verbose |
logical, if TRUE meaningful text output is generated. |
... |
these are passed to |
For a test with p-value output (as standard for tests in R) see multivariance.test
.
The "pearson_approx"
and "resample"
are approximately sharp. The latter is based on a resampling approach and thus much slower. The "distribution_free"
test might be very conservative.
The centered distance matrices can be prepared by cdms
. But note that for the test based on Pearson's approximation and for the resampling test, the data matrix has to be given.
Returns TRUE
if the hypothesis of independence is NOT rejected, otherwise FALSE
.
For the theoretic background see the references given on the main help page of this package: multivariance-package.
independence.test(coins(100)) #dependent sample which is 2-independent independence.test(coins(100),type = "resample") #dependent sample which is 2-independent independence.test(coins(100)[,2:3]) # independent sample independence.test(coins(100)[,2:3],type = "resample") # independent sample independence.test(coins(10),type = "resample") #dependent sample which is 2-independent independence.test(coins(10)[,2:3],type = "resample") #dependent sample which is 2-independent