stat_fit_tidy fits a model and returns a "tidy" version
of the model's summary, using 'tidy() methods from packages 'broom',
'broom.mixed', or other sources. To add the summary in tabular form use
stat_fit_tb instead of this statistic. When using
stat_fit_tidy() you will most likely want to change the default
mapping for label.
Usage
stat_fit_tidy(
mapping = NULL,
data = NULL,
geom = "text_npc",
method = "lm",
method.args = list(formula = y ~ x),
n.min = 2L,
tidy.args = list(),
label.x = "left",
label.y = "top",
hstep = 0,
vstep = NULL,
sanitize.names = FALSE,
position = "identity",
na.rm = FALSE,
show.legend = FALSE,
inherit.aes = TRUE,
...
)Arguments
- mapping
The aesthetic mapping, usually constructed with
aes. Only needs to be set at the layer level if you are overriding the plot defaults.- data
A layer specific dataset - only needed if you want to override the plot defaults.
- geom
The geometric object to use display the data
- method
character or function.
- method.args, tidy.args
list of arguments to pass to
method, and to [generics::tidy], respectively.- n.min
integer Minimum number of distinct values in the explanatory variable (on the rhs of formula) for fitting to the attempted.
- label.x, label.y
numericwith range 0..1 or character. Coordinates to be used for positioning the output, expressed in "normalized parent coordinates" or character string. If too short they will be recycled.- hstep, vstep
numeric in npc units, the horizontal and vertical step used between labels for different groups.
- sanitize.names
logical If true sanitize column names in the returned
datawith R'smake.names()function.- position
The position adjustment to use for overlapping points on this layer
- na.rm
a logical indicating whether NA values should be stripped before the computation proceeds.
- show.legend
logical. Should this layer be included in the legends?
NA, the default, includes if any aesthetics are mapped.FALSEnever includes, andTRUEalways includes.- inherit.aes
If
FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g.borders.- ...
other arguments passed on to
layer. This can include aesthetics whose values you want to set, not map. Seelayerfor more details.
Value
The output of tidy() is returned after reshaping it into a
single row. Grouping is respected, and the model fitted separately to each
group of data. The returned data object has one row for each group
within a panel. To use the intercept, note that output of tidy() is
renamed from (Intercept) to Intercept. Otherwise, the names
of the columns in the returned data are based on those returned by the
tidy() method for the model fit class returned by the fit function.
These will frequently differ from the name of values returned by the print
methods corresponding to the fit or test function used. To explore the
values returned by this statistic including the name of variables/columns,
which vary depending on the model fitting function and model formula, we
suggest the use of geom_debug. An example is shown
below. Names of columns as returned by default are not always syntactically
valid R names making it necessary to use back ticks to access them.
Syntactically valid names are guaranteed if sanitize.names = TRUE is
added to the call.
To explore the values returned by this statistic, which vary depending on the model fitting function and model formula we suggest the use of
geom_debug. An example is shown below.
Details
stat_fit_tidy together with stat_fit_glance
and stat_fit_augment, based on package 'broom' can be used
with a broad range of model fitting functions as supported at any given
time by 'broom'. In contrast to stat_poly_eq which can
generate text or expression labels automatically, for these functions the
mapping of aesthetic label needs to be explicitly supplied in the
call, and labels built on the fly.
A ggplot statistic receives as data a data frame that is not the one passed
as argument by the user, but instead a data frame with the variables mapped
to aesthetics. In other words, it respects the grammar of graphics and
consequently within arguments passed through method.args names of
aesthetics like $x$ and $y$ should be used instead of the original variable
names, while data is automatically passed the data frame. This helps ensure
that the model is fitted to the same data as plotted in other layers.
Note
The statistic stat_fit_tidy can be used only with
methods that accept formulas under any formal parameter name and a
data argument. Use ggplot2::stat_smooth() instead of
stat_fit_augment in production code if the additional features are
not needed.
Although arguments passed to parameter tidy.args will be
passed to [generics::tidy()] whether they are silently ignored or obeyed
depends on each specialization of [tidy()], so do carefully read the
documentation for the version of [tidy()] corresponding to the `method`
used to fit the model. You will also need to manually install the package,
such as 'broom', where the tidier you intend to use are defined.
Warning!
Not all `glance()` methods are defined in package 'broom'. `glance()` specializations for mixed models fits of classes `lme`, `nlme`, `lme4`, and many others are defined in package 'broom.mixed'.
Handling of grouping
stat_fit_tidy applies the function
given by method separately to each group of observations; in ggplot2
factors mapped to aesthetics generate a separate group for each level.
Because of this, stat_fit_tidy is not useful for annotating plots
with results from t.test() or ANOVA or ANCOVA. In such cases use
instead stat_fit_tb() which applies the model fitting per panel.
See also
broom and broom.mixed for details on how
the tidying of the result of model fits is done.
Other ggplot statistics for model fits:
stat_fit_augment(),
stat_fit_deviations(),
stat_fit_glance(),
stat_fit_residuals(),
stat_fit_tb()
Examples
# Package 'broom' needs to be installed to run these examples.
# We check availability before running them to avoid errors.
if (requireNamespace("broom", quietly = TRUE)) {
broom.installed <- TRUE
library(broom)
library(quantreg)
# Inspecting the returned data using geom_debug()
if (requireNamespace("gginnards", quietly = TRUE)) {
library(gginnards)
# This provides a quick way of finding out the names of the variables that
# are available for mapping to aesthetics. This is specially important for
# this stat as these names depend on the specific tidy() method used, which
# depends on the method used, such as lm(), used to fit the model.
# Regression by panel, default column names
ggplot(mtcars, aes(x = disp, y = mpg)) +
stat_smooth(method = "lm", formula = y ~ x + I(x^2)) +
geom_point(aes(colour = factor(cyl))) +
stat_fit_tidy(method = "lm",
method.args = list(formula = y ~ x + I(x^2)),
geom = "debug")
# Regression by panel, sanitized column names
ggplot(mtcars, aes(x = disp, y = mpg)) +
stat_smooth(method = "lm", formula = y ~ x + I(x^2)) +
geom_point(aes(colour = factor(cyl))) +
stat_fit_tidy(method = "lm",
method.args = list(formula = y ~ x + I(x^2)),
geom = "debug", sanitize.names = TRUE)
}
}
#> [1] "PANEL 1; group(s) -1; 'draw_function()' input 'data' (head):"
#> npcx npcy Intercept_estimate x_estimate I.x.2._estimate Intercept_se
#> 1 NA NA 35.8287 -0.1052732 0.0001255373 2.208819
#> x_se I.x.2._se Intercept_stat x_stat I.x.2._stat Intercept_p.value
#> 1 0.0202769 3.891214e-05 16.22075 -5.191783 3.226172 4.389937e-16
#> x_p.value I.x.2._p.value x y fm.class fm.method fm.formula
#> 1 1.488465e-05 0.003103547 91.145 32.725 lm lm y ~ x + I(x^2)
#> fm.formula.chr PANEL group
#> 1 y ~ x + I(x^2) 1 -1
# Regression by panel example
if (broom.installed)
ggplot(mtcars, aes(x = disp, y = mpg)) +
stat_smooth(method = "lm", formula = y ~ x) +
geom_point(aes(colour = factor(cyl))) +
stat_fit_tidy(method = "lm",
label.x = "right",
method.args = list(formula = y ~ x),
mapping = aes(label = sprintf("Slope = %.3g\np-value = %.3g",
after_stat(x_estimate),
after_stat(x_p.value))))
# Regression by group example
if (broom.installed)
ggplot(mtcars, aes(x = disp, y = mpg, colour = factor(cyl))) +
stat_smooth(method = "lm", formula = y ~ x) +
geom_point() +
stat_fit_tidy(method = "lm",
label.x = "right",
method.args = list(formula = y ~ x),
mapping = aes(label = sprintf("Slope = %.3g, p-value = %.3g",
after_stat(x_estimate),
after_stat(x_p.value))))
# Weighted regression example
if (broom.installed)
ggplot(mtcars, aes(x = disp, y = mpg, weight = cyl)) +
stat_smooth(method = "lm", formula = y ~ x) +
geom_point(aes(colour = factor(cyl))) +
stat_fit_tidy(method = "lm",
label.x = "right",
method.args = list(formula = y ~ x, weights = quote(weight)),
mapping = aes(label = sprintf("Slope = %.3g\np-value = %.3g",
after_stat(x_estimate),
after_stat(x_p.value))))
# Quantile regression
if (broom.installed)
ggplot(mtcars, aes(x = disp, y = mpg)) +
stat_smooth(method = "lm", formula = y ~ x) +
geom_point() +
stat_fit_tidy(method = "rq",
label.y = "bottom",
method.args = list(formula = y ~ x),
tidy.args = list(se.type = "nid"),
mapping = aes(label = sprintf("Slope = %.3g\np-value = %.3g",
after_stat(x_estimate),
after_stat(x_p.value))))
