Authors
+ +Citation
+ Source:DESCRIPTION
+ -
-
-
-
Grayson White. Maintainer, author. -
-
-
White G (2022). +gglm: Grammar of Graphics for Linear Model Diagnostic Plots. +R package version 1.0.0, https://github.com/graysonwhite/gglm. +
+@Manual{,
+ title = {gglm: Grammar of Graphics for Linear Model Diagnostic Plots},
+ author = {Grayson White},
+ year = {2022},
+ note = {R package version 1.0.0},
+ url = {https://github.com/graysonwhite/gglm},
+}
Authors
-- - - + + @@ -69,71 +65,86 @@
- ... +
Currently ignored. For extendability.
+
+- alpha +
Adjust transparency of points.
+
+
+- method +
Method for fitting the line to the points.
+
+
+- color +
Color of the line.
+
+
+- se +
Keep standard error bands around line?
+
+
+- ... +
Currently ignored. For extendability.
+
+- alpha +
Adjust transparency of points.
+
+
+- ... +
Currently ignored. For extendability.
+
+- alpha +
Adjust transparency of points.
+
+
+- ... +
Currently ignored. For extendability.
+
+- bins +
Adjust the number of bins.
+
+
+- ... +
Currently ignored. For extendability.
+
+- alpha +
Adjust transparency of points.
+
+
+- method +
Method for fitting the line to the points.
+
+
+- se +
Keep standard error bands around line?
+
+
+- color +
Color of the line.
+
+
+- ... +
Currently ignored. For extendability.
+
+
-gglm 
+
+
-
-
-Overview
-gglm, The Grammar of Graphics for Linear Model Diagnostics, is an R package and official ggplot2 extension that creates beautiful ggplot2 diagonostic plots for linear models that are easy to use and adhere to The Grammar of Graphics. The purpose of this package is to provide a sensible alternative to using the base-R plot() function to produce diagnostic plots for linear models.
-
-
-
-Installation
-You can now install gglm from CRAN, do so with this code:
-
-install.packages("gglm")
-Or, you can install the developmental version from GitHub:
-
-devtools::install_github("graysonwhite/gglm")
-
-
-
-Examples
-gglm has two main types of functions. First, the gglm() function for quickly creating the four main diagnostic plots, similar to when you call plot() on an lm type object. Second, the stat_*() functions, which produce diagnostic plots the align with The Grammar of Graphics by creating ggplot2 layers that allow for easy plotting of particular model diagnostic plots.
-
-
-Example 1: Quickly creating the four diagnostic plots with gglm()
+
+Overview
+
+gglm, The Grammar of Graphics for Linear Model Diagnostics, is an R package and official ggplot2 extension that creates beautiful diagnostic plots using ggplot2 for a variety of model objects. These diagnostic plots are easy to use and adhere to the Grammar of Graphics. The purpose of this package is to provide a sensible alternative to using the base-R plot() function to produce diagnostic plots for model objects. Currently, gglm supports all model objects that are supported by broom::augment(), broom.mixed::augment(), or ggplot2::fortify(). For example, objects that are outputted from stats::lm(), lme4::lmer(), brms::brm(), and many other common modeling functions will work with gglm. The function gglm::list_model_classes() provides a full list of model classes supported by gglm.
+
+
+Installation
+
+gglm can be installed from CRAN:
+
+install.packages("gglm")
+Or, the developmental version of gglm can be installed from GitHub:
+
+devtools::install_github("graysonwhite/gglm")
+
+
+Examples
+
+gglm has two main types of functions. First, the gglm() function is used for quickly creating the four main diagnostic plots, and behaves similarly to how plot() works on an lm type object. Second, the stat_*() functions are used to produce diagnostic plots by creating ggplot2 layers. These layers allow for plotting of particular model diagnostic plots within the ggplot2 framework.
+
+Example 1: Quickly creating the four diagnostic plots with gglm()
+
-
-library(gglm) # Load the package
-data(mtcars) # Load example data
-model <- lm(mpg ~ ., data = mtcars) # Create your model
-
-gglm(model) # Plot the four main diagnostic plots
+Consider a simple linear model used to predict miles per gallon with weight. We can fit this model with lm(), and then diagnose it easily by using gglm().
+
+library(gglm) # Load gglm
+
+model <- lm(mpg ~ wt, data = mtcars) # Fit the simple linear model
+
+gglm(model) # Plot the four main diagnostic plots
-
-
-
-Example 2: Using the Grammar of Graphics with the stat_*() functions
-
-library(ggplot2) # Need to load ggplot2
-
-ggplot(data = model) +
- stat_fitted_resid()
+Now, one may be interested in a more complicated model, such as a mixed model with a varying intercept on cyl, fit with the lme4 package. Luckily, gglm accommodates a variety of models and modeling packages, so the diagnostic plots for the mixed model can be created in the same way as they were for the simple linear model.
+
+library(lme4) # Load lme4 to fit the mixed model
+
+mixed_model <- lmer(mpg ~ wt + (1 | cyl), data = mtcars) # Fit the mixed model
+
+gglm(mixed_model) # Plot the four main diagnostic plots.
-
-# We can also add layers such as themes to these `ggplot`s and adjust features of the plot:
-ggplot(data = model) +
- stat_cooks_leverage(alpha = 1) +
- theme_minimal()
-
-
-
-
-
-Functions
-
-
-For quick and easy plotting
-gglm() plots the four default diagnostic plots when supplied an lm object. This function works similarly to plot.lm(), except that it displays the four diagnostic plots at once.
-
-
+
+Example 2: Using the Grammar of Graphics with the stat_*() functions
+
+gglm also provides functionality to stay within the Grammar of Graphics by providing functions that can be used as ggplot2 layers. An example of one of these functions is the stat_fitted_resid() function. With this function, we can take a closer look at just the fitted vs. residual plot from the mixed model fit in Example 1.
+
+ggplot(data = mixed_model) +
+ stat_fitted_resid()
+
+After taking a closer look, we may want to clean up the look of the plot for a presentation or a project. This can be done by adding other layers from ggplot2 to the plot. Note that any ggplot2 layers can be added on to any of the stat_*() functions provided by gglm.
+
+ggplot(data = mixed_model) +
+ stat_fitted_resid(alpha = 1) +
+ theme_bw() + # add a clean theme
+ labs(title = "Residual vs fitted values for the mixed model") + # change the title
+ theme(plot.title = element_text(hjust = 0.5)) # center the title
+
+Wow! What a beautiful and production-ready diagnostic plot!
+
+
+
+Functions
+
+
+For quick and easy plotting
+
+gglm() plots the four default diagnostic plots when supplied a model object (this is similar to plot.lm() in the case of an object generated by lm()). Note that can gglm() take many types of model object classes as its input, and possible model object classes can be seen with list_model_classes()
+
+
+Following the Grammar of Graphics
+
stat_normal_qq(), stat_fitted_resid(), stat_resid_hist(), stat_scale_location(), stat_cooks_leverage(), stat_cooks_obs(), and stat_resid_leverage() all are ggplot2 layers used to create individual diagnostic plots. To use these, follow Example 2.
+
+Other functions
+
+list_model_classes() lists the model classes compatible with gglm.
+
@@ -141,46 +152,56 @@
-
-
+
+
diff --git a/docs/reference/index.html b/docs/reference/index.html
index 0296ea5..72f1291 100644
--- a/docs/reference/index.html
+++ b/docs/reference/index.html
@@ -1,66 +1,12 @@
-
-
-
-
-
-
-
-Function reference • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-Function reference • gglm
-
-
+
+
-
-
-
-
-
-
-
-
+
Reference
-
+
-
-
-
+
+
diff --git a/docs/reference/list_model_classes.html b/docs/reference/list_model_classes.html
new file mode 100644
index 0000000..f836ad7
--- /dev/null
+++ b/docs/reference/list_model_classes.html
@@ -0,0 +1,121 @@
+
+list_model_classes — list_model_classes • gglm
+
+
+
+
+
+
+
+
+
+
+
+
+ Returns the possible model classes that `gglm` works with.
+
+
+
+ list_model_classes(...)
+
+
+
+ Arguments
+
+
+ Value
+
+
+A character vector containing the possible model classes that `gglm`
+works with.
+
+
+ Note
+ Note that these are not always the exact name of the class that that
+can be used. This is due to how some methods are written in the packages
+`gglm` imports. For example, the model class "merMod" refers to a variety of
+model outputs from `lme4`, even when the outputted class is not called
+"merMod".
+
+
+
+ Examples
+ list_model_classes()
+#> [1] "mlogit" "rma" "poissonmfx" "default"
+#> [5] "lmrob" "rqs" "prcomp" "rq"
+#> [9] "glmRob" "polr" "mjoint" "stl"
+#> [13] "glmmadmb" "survreg" "drc" "kmeans"
+#> [17] "fixest" "merMod" "nlrq" "factanal"
+#> [21] "htest" "lm" "glmrob" "smooth.spline"
+#> [25] "ivreg" "gam" "sarlm" "mfx"
+#> [29] "poLCA" "felm" "negbinmfx" "glmmTMB"
+#> [33] "glm" "clm" "NULL" "gamm4"
+#> [37] "speedlm" "Sarlm" "gls" "pam"
+#> [41] "decomposed.ts" "brmsfit" "speedglm" "logitmfx"
+#> [45] "betamfx" "data.frame" "plm" "Mclust"
+#> [49] "loess" "probitmfx" "coxph" "ranef.mer"
+#> [53] "lmRob" "betareg" "nls" "rlm"
+#> [57] "margins" "lme"
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/docs/reference/reexports.html b/docs/reference/reexports.html
new file mode 100644
index 0000000..8d6bece
--- /dev/null
+++ b/docs/reference/reexports.html
@@ -0,0 +1,89 @@
+
+Objects exported from other packages — reexports • gglm
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/docs/reference/stat_cooks_leverage-1.png b/docs/reference/stat_cooks_leverage-1.png
index 545f156..63abe04 100644
Binary files a/docs/reference/stat_cooks_leverage-1.png and b/docs/reference/stat_cooks_leverage-1.png differ
diff --git a/docs/reference/stat_cooks_leverage.html b/docs/reference/stat_cooks_leverage.html
index 6e29ee6..09b51f1 100644
--- a/docs/reference/stat_cooks_leverage.html
+++ b/docs/reference/stat_cooks_leverage.html
@@ -1,67 +1,12 @@
-
-
-
-
-
-
-
-stat_cooks_leverage — stat_cooks_leverage • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-stat_cooks_leverage — stat_cooks_leverage • gglm
-
-
-
-
+
+
-
-
-
-
-
-
+
stat_cooks_leverage
- Source: R/stat_cooks_leverage.R
+ Source: R/stat_cooks_leverage.R
stat_cooks_leverage.Rd
@@ -117,73 +49,74 @@ stat_cooks_leverage
Cook's Distance vs. Leverage
- stat_cooks_leverage(
- alpha = 0.5,
- method = "loess",
- color = "steelblue",
- se = FALSE,
- ...
-)
-
- Arguments
-
-
- alpha
- Adjust transparency of points.
-
- method
- Method for fitting the line to the points.
-
- color
- Color of the line.
-
- se
- Keep standard error bands around line?
-
- ...
- Currently ignored. For extendability.
-
-
- Value
-
- A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
-
- Examples
- data(mtcars)
-model <- lm(mpg ~ cyl + disp + hp, data = mtcars)
-ggplot2::ggplot(data = model) + stat_cooks_leverage()
-
+
+ stat_cooks_leverage(
+ alpha = 0.5,
+ method = "loess",
+ color = "steelblue",
+ se = FALSE,
+ ...
+)
+
+
+
+ Arguments
+
+
+ Value
+
+
+A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
+
+
+
+
-
-
-
+
+
diff --git a/docs/reference/stat_cooks_obs-1.png b/docs/reference/stat_cooks_obs-1.png
index 444ca57..f913629 100644
Binary files a/docs/reference/stat_cooks_obs-1.png and b/docs/reference/stat_cooks_obs-1.png differ
diff --git a/docs/reference/stat_cooks_obs.html b/docs/reference/stat_cooks_obs.html
index bf60eb2..0339165 100644
--- a/docs/reference/stat_cooks_obs.html
+++ b/docs/reference/stat_cooks_obs.html
@@ -1,67 +1,12 @@
-
-
-
-
-
-
-
-stat_cooks_obs — stat_cooks_obs • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-stat_cooks_obs — stat_cooks_obs • gglm
-
+
+
-
-
-
-
-
-
-
-
-
+
@@ -117,51 +49,52 @@ stat_cooks_obs
`ggplot2` layer for plotting cook's distance by observation number.
- stat_cooks_obs(...)
+
+ stat_cooks_obs(...)
+
- Arguments
-
-
- ...
- Currently ignored. For extendability.
-
+
+
+ Value
+
- A `ggplot2` layer for plotting cook's distance by observation number.
+A `ggplot2` layer for plotting cook's distance by observation number.
+
- Examples
- data(mtcars)
-model <- lm(mpg ~ cyl + disp + hp, data = mtcars)
-ggplot2::ggplot(data = model) + stat_cooks_obs()
-
+
+
-
-
-
+
+
diff --git a/docs/reference/stat_fitted_resid-1.png b/docs/reference/stat_fitted_resid-1.png
index 84ad1dd..6090244 100644
Binary files a/docs/reference/stat_fitted_resid-1.png and b/docs/reference/stat_fitted_resid-1.png differ
diff --git a/docs/reference/stat_fitted_resid.html b/docs/reference/stat_fitted_resid.html
index 3c7f1bf..7b4f580 100644
--- a/docs/reference/stat_fitted_resid.html
+++ b/docs/reference/stat_fitted_resid.html
@@ -1,67 +1,12 @@
-
-
-
-
-
-
-
-stat_fitted_resid — stat_fitted_resid • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-stat_fitted_resid — stat_fitted_resid • gglm
+
+
-
-
-
-
-
-
-
-
-
-
+
stat_fitted_resid
- Source: R/stat_fitted_resid.R
+ Source: R/stat_fitted_resid.R
stat_fitted_resid.Rd
@@ -117,55 +49,56 @@ stat_fitted_resid
`ggplot2` layer for plotting a fitted vs. residual scatter plot.
- stat_fitted_resid(alpha = 0.5, ...)
-
- Arguments
-
-
- alpha
- Adjust transparency of points.
-
- ...
- Currently ignored. For extendability.
-
-
- Value
-
- A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
-
- Examples
- data(mtcars)
-model <- lm(mpg ~ cyl + disp + hp, data = mtcars)
-ggplot2::ggplot(data = model) + stat_fitted_resid()
-
+
+ stat_fitted_resid(alpha = 0.5, ...)
+
+
+
+ Arguments
+
+
+ Value
+
+
+A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
+
+
+
+
-
-Overview
-gglm, The Grammar of Graphics for Linear Model Diagnostics, is an R package and official ggplot2 extension that creates beautiful ggplot2 diagonostic plots for linear models that are easy to use and adhere to The Grammar of Graphics. The purpose of this package is to provide a sensible alternative to using the base-R plot() function to produce diagnostic plots for linear models.
-Installation
-You can now install gglm from CRAN, do so with this code:
-install.packages("gglm")
Or, you can install the developmental version from GitHub:
--devtools::install_github("graysonwhite/gglm")
-Examples
-gglm has two main types of functions. First, the gglm() function for quickly creating the four main diagnostic plots, similar to when you call plot() on an lm type object. Second, the stat_*() functions, which produce diagnostic plots the align with The Grammar of Graphics by creating ggplot2 layers that allow for easy plotting of particular model diagnostic plots.
-Example 1: Quickly creating the four diagnostic plots with gglm()
+
+Overview
+
+gglm, The Grammar of Graphics for Linear Model Diagnostics, is an R package and official ggplot2 extension that creates beautiful diagnostic plots using ggplot2 for a variety of model objects. These diagnostic plots are easy to use and adhere to the Grammar of Graphics. The purpose of this package is to provide a sensible alternative to using the base-R plot() function to produce diagnostic plots for model objects. Currently, gglm supports all model objects that are supported by broom::augment(), broom.mixed::augment(), or ggplot2::fortify(). For example, objects that are outputted from stats::lm(), lme4::lmer(), brms::brm(), and many other common modeling functions will work with gglm. The function gglm::list_model_classes() provides a full list of model classes supported by gglm.
+
+
+Installation
+
+gglm can be installed from CRAN:
+
+install.packages("gglm")
+Or, the developmental version of gglm can be installed from GitHub:
+
+devtools::install_github("graysonwhite/gglm")
+
+
+Examples
+
+gglm has two main types of functions. First, the gglm() function is used for quickly creating the four main diagnostic plots, and behaves similarly to how plot() works on an lm type object. Second, the stat_*() functions are used to produce diagnostic plots by creating ggplot2 layers. These layers allow for plotting of particular model diagnostic plots within the ggplot2 framework.
+
+Example 1: Quickly creating the four diagnostic plots with gglm()
+
-
-library(gglm) # Load the package
-data(mtcars) # Load example data
-model <- lm(mpg ~ ., data = mtcars) # Create your model
-
-gglm(model) # Plot the four main diagnostic plots
+Consider a simple linear model used to predict miles per gallon with weight. We can fit this model with lm(), and then diagnose it easily by using gglm().
+
+library(gglm) # Load gglm
+
+model <- lm(mpg ~ wt, data = mtcars) # Fit the simple linear model
+
+gglm(model) # Plot the four main diagnostic plots
-
-
-
-Example 2: Using the Grammar of Graphics with the stat_*() functions
-
-library(ggplot2) # Need to load ggplot2
-
-ggplot(data = model) +
- stat_fitted_resid()
+Now, one may be interested in a more complicated model, such as a mixed model with a varying intercept on cyl, fit with the lme4 package. Luckily, gglm accommodates a variety of models and modeling packages, so the diagnostic plots for the mixed model can be created in the same way as they were for the simple linear model.
+
+library(lme4) # Load lme4 to fit the mixed model
+
+mixed_model <- lmer(mpg ~ wt + (1 | cyl), data = mtcars) # Fit the mixed model
+
+gglm(mixed_model) # Plot the four main diagnostic plots.
-
-# We can also add layers such as themes to these `ggplot`s and adjust features of the plot:
-ggplot(data = model) +
- stat_cooks_leverage(alpha = 1) +
- theme_minimal()
-
-
-
-
-
-Functions
-
-
-For quick and easy plotting
-gglm() plots the four default diagnostic plots when supplied an lm object. This function works similarly to plot.lm(), except that it displays the four diagnostic plots at once.
-
-
+
+Example 2: Using the Grammar of Graphics with the stat_*() functions
+
+gglm also provides functionality to stay within the Grammar of Graphics by providing functions that can be used as ggplot2 layers. An example of one of these functions is the stat_fitted_resid() function. With this function, we can take a closer look at just the fitted vs. residual plot from the mixed model fit in Example 1.
+
+ggplot(data = mixed_model) +
+ stat_fitted_resid()
+
+After taking a closer look, we may want to clean up the look of the plot for a presentation or a project. This can be done by adding other layers from ggplot2 to the plot. Note that any ggplot2 layers can be added on to any of the stat_*() functions provided by gglm.
+
+ggplot(data = mixed_model) +
+ stat_fitted_resid(alpha = 1) +
+ theme_bw() + # add a clean theme
+ labs(title = "Residual vs fitted values for the mixed model") + # change the title
+ theme(plot.title = element_text(hjust = 0.5)) # center the title
+
+Wow! What a beautiful and production-ready diagnostic plot!
+
+
+
+Functions
+
+
+For quick and easy plotting
+
+gglm() plots the four default diagnostic plots when supplied a model object (this is similar to plot.lm() in the case of an object generated by lm()). Note that can gglm() take many types of model object classes as its input, and possible model object classes can be seen with list_model_classes()
+
+
+Following the Grammar of Graphics
+
stat_normal_qq(), stat_fitted_resid(), stat_resid_hist(), stat_scale_location(), stat_cooks_leverage(), stat_cooks_obs(), and stat_resid_leverage() all are ggplot2 layers used to create individual diagnostic plots. To use these, follow Example 2.
+
+Other functions
+
+list_model_classes() lists the model classes compatible with gglm.
+
Overview +
+gglm, The Grammar of Graphics for Linear Model Diagnostics, is an R package and official ggplot2 extension that creates beautiful diagnostic plots using ggplot2 for a variety of model objects. These diagnostic plots are easy to use and adhere to the Grammar of Graphics. The purpose of this package is to provide a sensible alternative to using the base-R plot() function to produce diagnostic plots for model objects. Currently, gglm supports all model objects that are supported by broom::augment(), broom.mixed::augment(), or ggplot2::fortify(). For example, objects that are outputted from stats::lm(), lme4::lmer(), brms::brm(), and many other common modeling functions will work with gglm. The function gglm::list_model_classes() provides a full list of model classes supported by gglm.
Installation +
+gglm can be installed from CRAN:
+install.packages("gglm")Or, the developmental version of gglm can be installed from GitHub:
+devtools::install_github("graysonwhite/gglm")Examples +
+gglm has two main types of functions. First, the gglm() function is used for quickly creating the four main diagnostic plots, and behaves similarly to how plot() works on an lm type object. Second, the stat_*() functions are used to produce diagnostic plots by creating ggplot2 layers. These layers allow for plotting of particular model diagnostic plots within the ggplot2 framework.
Example 1: Quickly creating the four diagnostic plots with gglm()
+
--library(gglm) # Load the package -data(mtcars) # Load example data -model <- lm(mpg ~ ., data = mtcars) # Create your model - -gglm(model) # Plot the four main diagnostic plots
Consider a simple linear model used to predict miles per gallon with weight. We can fit this model with lm(), and then diagnose it easily by using gglm().
+library(gglm) # Load gglm
+
+model <- lm(mpg ~ wt, data = mtcars) # Fit the simple linear model
+
+gglm(model) # Plot the four main diagnostic plots
-Example 2: Using the Grammar of Graphics with the stat_*() functions
--library(ggplot2) # Need to load ggplot2 - -ggplot(data = model) + - stat_fitted_resid()
Now, one may be interested in a more complicated model, such as a mixed model with a varying intercept on cyl, fit with the lme4 package. Luckily, gglm accommodates a variety of models and modeling packages, so the diagnostic plots for the mixed model can be created in the same way as they were for the simple linear model.
+library(lme4) # Load lme4 to fit the mixed model
+
+mixed_model <- lmer(mpg ~ wt + (1 | cyl), data = mtcars) # Fit the mixed model
+
+gglm(mixed_model) # Plot the four main diagnostic plots.
-# We can also add layers such as themes to these `ggplot`s and adjust features of the plot: -ggplot(data = model) + - stat_cooks_leverage(alpha = 1) + - theme_minimal()
-Functions
--For quick and easy plotting
-gglm() plots the four default diagnostic plots when supplied an lm object. This function works similarly to plot.lm(), except that it displays the four diagnostic plots at once.
Example 2: Using the Grammar of Graphics with the stat_*() functions
+
+gglm also provides functionality to stay within the Grammar of Graphics by providing functions that can be used as ggplot2 layers. An example of one of these functions is the stat_fitted_resid() function. With this function, we can take a closer look at just the fitted vs. residual plot from the mixed model fit in Example 1.
+ggplot(data = mixed_model) +
+ stat_fitted_resid()
After taking a closer look, we may want to clean up the look of the plot for a presentation or a project. This can be done by adding other layers from ggplot2 to the plot. Note that any ggplot2 layers can be added on to any of the stat_*() functions provided by gglm.
+ggplot(data = mixed_model) +
+ stat_fitted_resid(alpha = 1) +
+ theme_bw() + # add a clean theme
+ labs(title = "Residual vs fitted values for the mixed model") + # change the title
+ theme(plot.title = element_text(hjust = 0.5)) # center the title
Wow! What a beautiful and production-ready diagnostic plot!
+Functions +
+For quick and easy plotting +
+gglm() plots the four default diagnostic plots when supplied a model object (this is similar to plot.lm() in the case of an object generated by lm()). Note that can gglm() take many types of model object classes as its input, and possible model object classes can be seen with list_model_classes()
Following the Grammar of Graphics +
stat_normal_qq(), stat_fitted_resid(), stat_resid_hist(), stat_scale_location(), stat_cooks_leverage(), stat_cooks_obs(), and stat_resid_leverage() all are ggplot2 layers used to create individual diagnostic plots. To use these, follow Example 2.
Other functions +
+list_model_classes() lists the model classes compatible with gglm.
-
-
+
+
diff --git a/docs/reference/index.html b/docs/reference/index.html
index 0296ea5..72f1291 100644
--- a/docs/reference/index.html
+++ b/docs/reference/index.html
@@ -1,66 +1,12 @@
-
-
-
-
-
-
-
-Function reference • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-Function reference • gglm
-
-
+
+
-
-
-
-
-
-
-
-
+
Reference
-
+
-
-
-
+
+
diff --git a/docs/reference/list_model_classes.html b/docs/reference/list_model_classes.html
new file mode 100644
index 0000000..f836ad7
--- /dev/null
+++ b/docs/reference/list_model_classes.html
@@ -0,0 +1,121 @@
+
+list_model_classes — list_model_classes • gglm
+
+
+
+
+
+
+
+
+
+
+
+
+ Returns the possible model classes that `gglm` works with.
+
+
+
+ list_model_classes(...)
+
+
+
+ Arguments
+
+
+ Value
+
+
+A character vector containing the possible model classes that `gglm`
+works with.
+
+
+ Note
+ Note that these are not always the exact name of the class that that
+can be used. This is due to how some methods are written in the packages
+`gglm` imports. For example, the model class "merMod" refers to a variety of
+model outputs from `lme4`, even when the outputted class is not called
+"merMod".
+
+
+
+ Examples
+ list_model_classes()
+#> [1] "mlogit" "rma" "poissonmfx" "default"
+#> [5] "lmrob" "rqs" "prcomp" "rq"
+#> [9] "glmRob" "polr" "mjoint" "stl"
+#> [13] "glmmadmb" "survreg" "drc" "kmeans"
+#> [17] "fixest" "merMod" "nlrq" "factanal"
+#> [21] "htest" "lm" "glmrob" "smooth.spline"
+#> [25] "ivreg" "gam" "sarlm" "mfx"
+#> [29] "poLCA" "felm" "negbinmfx" "glmmTMB"
+#> [33] "glm" "clm" "NULL" "gamm4"
+#> [37] "speedlm" "Sarlm" "gls" "pam"
+#> [41] "decomposed.ts" "brmsfit" "speedglm" "logitmfx"
+#> [45] "betamfx" "data.frame" "plm" "Mclust"
+#> [49] "loess" "probitmfx" "coxph" "ranef.mer"
+#> [53] "lmRob" "betareg" "nls" "rlm"
+#> [57] "margins" "lme"
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/docs/reference/reexports.html b/docs/reference/reexports.html
new file mode 100644
index 0000000..8d6bece
--- /dev/null
+++ b/docs/reference/reexports.html
@@ -0,0 +1,89 @@
+
+Objects exported from other packages — reexports • gglm
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/docs/reference/stat_cooks_leverage-1.png b/docs/reference/stat_cooks_leverage-1.png
index 545f156..63abe04 100644
Binary files a/docs/reference/stat_cooks_leverage-1.png and b/docs/reference/stat_cooks_leverage-1.png differ
diff --git a/docs/reference/stat_cooks_leverage.html b/docs/reference/stat_cooks_leverage.html
index 6e29ee6..09b51f1 100644
--- a/docs/reference/stat_cooks_leverage.html
+++ b/docs/reference/stat_cooks_leverage.html
@@ -1,67 +1,12 @@
-
-
-
-
-
-
-
-stat_cooks_leverage — stat_cooks_leverage • gglm
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-stat_cooks_leverage — stat_cooks_leverage • gglm
-
-
-
-
+
+
-
-
-
-
-
-
+
stat_cooks_leverage
- Source: R/stat_cooks_leverage.R
+ Source: R/stat_cooks_leverage.R
stat_cooks_leverage.Rd
@@ -117,73 +49,74 @@ stat_cooks_leverage
Cook's Distance vs. Leverage
- stat_cooks_leverage(
- alpha = 0.5,
- method = "loess",
- color = "steelblue",
- se = FALSE,
- ...
-)
-
- Arguments
-
-
- alpha
- Adjust transparency of points.
-
- method
- Method for fitting the line to the points.
-
- color
- Color of the line.
-
- se
- Keep standard error bands around line?
-
- ...
- Currently ignored. For extendability.
-
-
- Value
-
- A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
-
- Examples
- data(mtcars)
-model <- lm(mpg ~ cyl + disp + hp, data = mtcars)
-ggplot2::ggplot(data = model) + stat_cooks_leverage()
-
+
+ stat_cooks_leverage(
+ alpha = 0.5,
+ method = "loess",
+ color = "steelblue",
+ se = FALSE,
+ ...
+)
+
+
+
+ Arguments
+
+
+ Value
+
+
+A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
+
+
+
+
-
Reference
Returns the possible model classes that `gglm` works with.
+list_model_classes(...)Arguments
+Value
+ + +A character vector containing the possible model classes that `gglm` +works with.
+Note
+Note that these are not always the exact name of the class that that +can be used. This is due to how some methods are written in the packages +`gglm` imports. For example, the model class "merMod" refers to a variety of +model outputs from `lme4`, even when the outputted class is not called +"merMod".
+Examples
+list_model_classes()
+#> [1] "mlogit" "rma" "poissonmfx" "default"
+#> [5] "lmrob" "rqs" "prcomp" "rq"
+#> [9] "glmRob" "polr" "mjoint" "stl"
+#> [13] "glmmadmb" "survreg" "drc" "kmeans"
+#> [17] "fixest" "merMod" "nlrq" "factanal"
+#> [21] "htest" "lm" "glmrob" "smooth.spline"
+#> [25] "ivreg" "gam" "sarlm" "mfx"
+#> [29] "poLCA" "felm" "negbinmfx" "glmmTMB"
+#> [33] "glm" "clm" "NULL" "gamm4"
+#> [37] "speedlm" "Sarlm" "gls" "pam"
+#> [41] "decomposed.ts" "brmsfit" "speedglm" "logitmfx"
+#> [45] "betamfx" "data.frame" "plm" "Mclust"
+#> [49] "loess" "probitmfx" "coxph" "ranef.mer"
+#> [53] "lmRob" "betareg" "nls" "rlm"
+#> [57] "margins" "lme"
+stat_cooks_leverage
- Source:R/stat_cooks_leverage.R
+ Source: R/stat_cooks_leverage.R
stat_cooks_leverage.Rdstat_cooks_leverage
Cook's Distance vs. Leverage
stat_cooks_leverage( - alpha = 0.5, - method = "loess", - color = "steelblue", - se = FALSE, - ... -)- -
Arguments
-| alpha | -Adjust transparency of points. |
-
|---|---|
| method | -Method for fitting the line to the points. |
-
| color | -Color of the line. |
-
| se | -Keep standard error bands around line? |
-
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_cooks_leverage() -
stat_cooks_leverage(
+ alpha = 0.5,
+ method = "loess",
+ color = "steelblue",
+ se = FALSE,
+ ...
+)Arguments
+Value
+ + +A `ggplot2` layer for plotting Cook's Distance vs. Leverage.
+stat_cooks_obs
`ggplot2` layer for plotting cook's distance by observation number.
stat_cooks_obs(...)+
stat_cooks_obs(...)Arguments
-| ... | -Currently ignored. For extendability. |
-
|---|
Value
+ -A `ggplot2` layer for plotting cook's distance by observation number.
+A `ggplot2` layer for plotting cook's distance by observation number.
+Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_cooks_obs() -
stat_fitted_resid
- Source:R/stat_fitted_resid.R
+ Source: R/stat_fitted_resid.R
stat_fitted_resid.Rdstat_fitted_resid
`ggplot2` layer for plotting a fitted vs. residual scatter plot.
stat_fitted_resid(alpha = 0.5, ...)- -
Arguments
-| alpha | -Adjust transparency of points. |
-
|---|---|
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_fitted_resid() -
stat_fitted_resid(alpha = 0.5, ...)Arguments
+Value
+ + +A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
+stat_normal_qq
Normal QQ plot.
stat_normal_qq(alpha = 0.5, ...)- -
Arguments
-| alpha | -Adjust transparency of points. |
-
|---|---|
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting a Normal Q-Q plot.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_normal_qq() -
stat_normal_qq(alpha = 0.5, ...)Arguments
+Value
+ + +A `ggplot2` layer for plotting a Normal Q-Q plot.
+stat_resid_hist
Visualize the distribution of the residuals of a model.
stat_resid_hist(bins = 30, ...)- -
Arguments
-| bins | -Adjust the number of bins. |
-
|---|---|
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting a histogram of residuals.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_resid_hist() -
stat_resid_hist(bins = 30, ...)Arguments
+Value
+ + +A `ggplot2` layer for plotting a histogram of residuals.
+stat_resid_leverage
- Source:R/stat_resid_leverage.R
+ Source: R/stat_resid_leverage.R
stat_resid_leverage.Rdstat_resid_leverage
Residual vs. leverage plot.
stat_resid_leverage( - alpha = 0.5, - method = "loess", - se = FALSE, - color = "steelblue", - ... -)- -
Arguments
-| alpha | -Adjust transparency of points. |
-
|---|---|
| method | -Method for fitting the line to the points. |
-
| se | -Keep standard error bands around line? |
-
| color | -Color of the line. |
-
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_resid_leverage() -
stat_resid_leverage(
+ alpha = 0.5,
+ method = "loess",
+ se = FALSE,
+ color = "steelblue",
+ ...
+)Arguments
+Value
+ + +A `ggplot2` layer for plotting a fitted vs. residual scatter plot.
+stat_scale_location
- Source:R/stat_scale_location.R
+ Source: R/stat_scale_location.R
stat_scale_location.Rdstat_scale_location
Scale location diagnostic plot.
stat_scale_location( - alpha = 0.5, - na.rm = TRUE, - se = FALSE, - method = "loess", - color = "steelblue", - ... -)- -
Arguments
-| alpha | -Adjust the transparency of points. |
-
|---|---|
| na.rm | -Remove points with value NA? |
-
| se | -Keep standard error bands around line? |
-
| method | -Method for fitting the line to the points. |
-
| color | -Color of the line. |
-
| ... | -Currently ignored. For extendability. |
-
Value
- -A `ggplot2` layer for plotting the scale location diagnostic plot.
- -Examples
-+data(mtcars) -model <- lm(mpg ~ cyl + disp + hp, data = mtcars) -ggplot2::ggplot(data = model) + stat_scale_location() -
stat_scale_location(
+ alpha = 0.5,
+ na.rm = TRUE,
+ se = FALSE,
+ method = "loess",
+ color = "steelblue",
+ ...
+)Arguments
+- alpha +
Adjust the transparency of points.
+
+
+- na.rm +
Remove points with value NA?
+
+
+- se +
Keep standard error bands around line?
+
+
+- method +
Method for fitting the line to the points.
+
+
+- color +
Color of the line.
+
+
+- ... +
Currently ignored. For extendability.
+
+
Value
+ + +A `ggplot2` layer for plotting the scale location diagnostic plot.
+