New features
- The Peto-Peto test for right-censored data is now available
(see ?logrank_test and ?logrank_weight).
- The Moore-Penrose inverse of the conditional covariance matrix
can now be extracted (see ?covariance).
- For tests of conditional independence within blocks, the
partial linear statistic for each block and its conditional
expectation and variance as well as its conditional covariance
and corresponding Moore-Penrose inverse can now be extracted
(see ?statistic, ?expectation, ?variance and ?covariance).
Bug fixes
- Exact multivariate two-sample tests with quadratic test
statistics appeared to work but returned nonsense p-values; it
now results in an error.
- Extraction of the standardized linear statistic from objects of
class "IndependenceLinearStatistic" resulted in an error.
User-visible changes
- Extraction of the conditional expectation or variance now
returns a matrix instead of a vector (for consistency with
linear statistics and p-values).
- The test size is now computed more efficiently.
- Documentation updates.
Other changes
- The internal storage of the linear statistic and its
conditional expectation and covariance, i.e., slots
linearstatistic, expectation and covariance in classes
inheriting from "IndependenceLinearStatistic", as well as the
Moore-Penrose inverse of the conditional covariance, i.e., slot
covarianceplus in classes inheriting from
"QuadTypeIndependenceTestStatistic", has been changed. In
particular, the conditional covariance and its Moore-Penrose
inverse now use a memory-efficient packed format.
- R >=3.6.0 and package libcoin >=1.0-5 are now required.
Deprecated and defunct
- Classes "Variance", "CovarianceMatrix" and "VarCovar" are now
deprecated.