The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
grouping and
grouping_strip_position arguments from
ggforestplot(). Use facet and
facet_strip_position instead.add_favors() for composing two-sided directional
arrows and labels beneath the forest-plot panel. The fixed-height footer
respects log scales, custom limits and expansion, and remains aligned
when used after add_forest_table() or
add_split_table().subgroup mappings for mixed hierarchical
displays, allowing standalone covariates and contiguous categorical
blocks to share a forest plot. Subgroup p-values can be delegated as
“overall” or “level” via p_method in
tidy_forest_model() (#11)tidy_forest_model() and fitted-model
as_forest_data() methods now use
marginaleffects to derive average slopes or comparisons
from the original fit without refitting subgroup models or displaying
raw interaction coefficients. Conservative automatic selection supports
one continuous-by- factor interaction, while explicit selection supports
factor comparisons and preserves additive, odds-ratio, ratio, and
hazard-ratio scales.add_forest_table() and
add_split_table() now use the same vertical dodge as their
plotted points, keeping table text aligned at different output sizes and
with custom dodge_width values.group columns now retain their level
order in legends, vertically dodged estimates, and aligned forest-table
values.term_header, n_header,
events_header, and p_header in
add_forest_table() and add_split_table().
Relabel displayed headers with the column_labels named
vector instead.forest_data S3 class as the package’s stable
interchange format. It stores validated effect-scale, axis,
confidence-level, reference-value, source-model, source-package, and
source-column metadata. (#17)as_forest_data() into an S3 generic with
methods for data frames, existing forest_data objects,
linear and generalized linear models, Cox models, and supported
mixed-model classes. (#19)ggforestplot() to consume the
forest_data contract instead of determining plotting
behavior from the original model class.forest_metadata() for inspecting the semantic and
provenance metadata associated with a forest_data
object.estimate_scale = "ratio" and
axis_transform = "log10"; unexponentiated log-link
coefficients use estimate_scale = "log" and an identity
axis.bind_forest_models() now returns
forest_data and validates compatible estimate scales, axis
transformations, reference values, and confidence levels before
combining models.forest_data; provenance records model classes,
package names, and source column mappings instead.tidy_forest_model() remains available as a
compatibility wrapper around the new as_forest_data() model
methods."group" wherever desired in columns,
left_columns, or right_columns, and rename it
through column_labels like any other table column.add_forest_table() now supports
table_width and plot_width for controlling the
relative widths of the two composed panels.add_forest_table() specific to data-frame/plot
inheritance.show_terms, show_n, show_events,
show_estimate, and show_p from
add_forest_table() and add_split_table(). Use
columns, left_columns, and
right_columns to choose table columns explicitly.tidy_forest_model() and
ggforestplot() when broom.mixed is installed.
Mixed-model tidiers are restricted to fixed effects so random-effect
parameter rows are not plotted as terms. (#21)ggforestplot() via ci_limits, with optional
arrowheads for intervals extending beyond the displayed range.
(#18)bind_forest_models() to stack multiple fitted
models into one grouped forest-plot data frame. (#16)term, estimate, conf.low,
and conf.high are required. Optional table and grouping
columns are validated only when used.ggforestplot() output now respects factor level
order in the facet column, allowing users to control facet
ordering directly from their data.ggforestplot() output when users add
scale_y_discrete(limits = ...), preserving per-facet row
filtering while accepting visible term labels. (#20)ggforestplot():
ref_line now takes the numeric reference value directly,
and NULL hides the line.ref_label, ref_linetype, and
ref_color.facet and facet_strip_position as
clearer names for grouped plot panels. The older grouping
and grouping_strip_position arguments now warn and continue
to work.linewidth for confidence interval widths. The
older line_size argument now warns and continues to
work.columns, left_columns, and
right_columns selections.stripe_alpha to control row stripe transparency
across plots, side tables, and split tables. (#7)estimate_digits, interval_digits, and
p_digits.ref_line, ref_line_value, and
ref_line_label to standardize reference-line naming while
keeping zero_line arguments backward compatible.term_labels, a named-vector relabeling helper for
displayed model terms.add_forest_table(columns = ...) and
split-table column selection to support arbitrary preserved data columns
in addition to built-in columns.column_labels, a named-vector helper for
relabeling displayed table column headers.ci table column and
ci_fmt so users can display point estimates and confidence
intervals in separate columns. conf.low and
conf.high are accepted as aliases for ci.events column support across
ggforestplot(), as_forest_data(),
add_forest_table(), and add_split_table().
(#2) (#3) (Thanks @sritchie73 for the suggestion)add_forest_table() now allows for custom column
ordering via the columns argument.NAMESPACE and .Rd files.add_forest_table() and
add_split_table() for plot-table composition.These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.