Nothing
wls
(weighted least squares) in function names is now replaced with gls
(generalised least squars) to more properly reflect the scope of the functionality.
For example, the function wlsPower()
is now called glsPower()
- although the
former version still works and throws a warning. compute_InfoContent()
plot.glsPower()
there now is an option to manually set the font size of the
annotation in the influence plotswlsPower()
now also computes the information content of
cluster-period cells. Computation is currently done twice, once with a general formula
and once explicitly. Information content of whole periods or clusters is also computed.plot.wlsPower()
recieved multiple updates:annotations = <TRUE/FALSE>
show_colorbar
to hide colour bars was addedmarginal_plots
to hide marginal plots on whole periods or clusters was added.wlsPower()
now has an argument alpha_012
that offers an alternative
way to specifiy the correlation matrix.wlsPower()
, the argument AR
now accepts a vector of up to three values.
This allows to specifiy autoregressive structures for only a subset of: random cluster intercept,
random intervention effect and random subject intercept. plot.wlsPower
now produces up to three plots, the projection matrix, the intervention design and the covariance matrix.Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.