-
-Additionally, there is also a `grouped_` variant of this function that
-makes it easy to repeat the same operation across a **single** grouping
-variable:
+informative or change some of the default options. Additionally, there
+is also a `grouped_` variant of this function that makes it easy to
+repeat the same operation across a **single** grouping variable:
``` r
# for reproducibility
@@ -261,10 +235,7 @@ set.seed(123)
# plot
grouped_ggbetweenstats(
- data = dplyr::filter(
- .data = movies_long,
- genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
- ),
+ data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
x = mpaa,
y = length,
grouping.var = genre, # grouping variable
@@ -278,12 +249,12 @@ grouped_ggbetweenstats(
caption = substitute(paste(italic("Source"), ": IMDb (Internet Movie Database)")),
palette = "default_jama",
package = "ggsci",
- plotgrid.args = list(nrow = 2),
+ plotgrid.args = list(nrow = 1),
annotation.args = list(title = "Differences in movie length by mpaa ratings for different genres")
)
```
-
+
Note here that the function can be used to tag outliers!
@@ -510,10 +481,7 @@ set.seed(123)
# plot
grouped_gghistostats(
- data = dplyr::filter(
- .data = movies_long,
- genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
- ),
+ data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
x = budget,
test.value = 50,
type = "nonparametric",
@@ -524,7 +492,7 @@ grouped_gghistostats(
ggtheme = ggthemes::theme_tufte(),
# modify the defaults from `ggstatsplot` for each plot
ggplot.component = ggplot2::labs(caption = "Source: IMDB.com"),
- plotgrid.args = list(nrow = 2),
+ plotgrid.args = list(nrow = 1),
annotation.args = list(title = "Movies budgets for different genres")
)
```
@@ -670,7 +638,7 @@ set.seed(123)
# plot
ggscatterstats(
- data = dplyr::filter(.data = movies_long, genre == "Action"),
+ data = dplyr::filter(movies_long, genre == "Action"),
x = budget,
y = rating,
type = "robust", # type of test that needs to be run
@@ -703,10 +671,7 @@ set.seed(123)
# plot
grouped_ggscatterstats(
- data = dplyr::filter(
- .data = movies_long,
- genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
- ),
+ data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
x = rating,
y = length,
grouping.var = genre, # grouping variable
@@ -717,8 +682,8 @@ grouped_ggscatterstats(
ggplot.component = list(
ggplot2::scale_x_continuous(breaks = seq(2, 9, 1), limits = (c(2, 9)))
),
- plotgrid.args = list(nrow = 2),
- annotation.args = list(title = "Relationship between movie length by IMDB ratings for different genres")
+ plotgrid.args = list(nrow = 1),
+ annotation.args = list(title = "Relationship between movie length and IMDB ratings")
)
```
@@ -781,10 +746,7 @@ set.seed(123)
# plot
grouped_ggcorrmat(
- data = dplyr::filter(
- .data = movies_long,
- genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
- ),
+ data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
type = "robust", # correlation method
colors = c("#cbac43", "white", "#550000"),
grouping.var = genre, # grouping variable
@@ -961,6 +923,8 @@ ggpiestats(
data = mtcars,
x = am,
y = cyl,
+ package = "wesanderson",
+ palette = "Royal1",
title = "Dataset: Motor Trend Car Road Tests", # title for the plot
legend.title = "Transmission", # title for the legend
caption = substitute(paste(italic("Source"), ": 1974 Motor Trend US magazine"))
@@ -975,42 +939,10 @@ ggpiestats(
effect size + CIs 
-
-Additionally, there is also a `grouped_` variant of this function that
-makes it easy to repeat the same operation across a **single** grouping
-variable. Following example is a case where the theoretical question is
-about proportions for different levels of a single nominal variable:
+There is also a `grouped_` variant of this function that makes it easy
+to repeat the same operation across a **single** grouping variable.
+Following example is a case where the theoretical question is about
+proportions for different levels of a single nominal variable:
``` r
# for reproducibility
@@ -1018,18 +950,16 @@ set.seed(123)
# plot
grouped_ggpiestats(
- data = movies_long,
- x = genre,
- grouping.var = mpaa, # grouping variable
+ data = mtcars,
+ x = cyl,
+ grouping.var = am, # grouping variable
label.repel = TRUE, # repel labels (helpful for overlapping labels)
package = "ggsci", # package from which color palette is to be taken
- palette = "default_ucscgb", # choosing a different color palette
- annotation.args = list(title = "Composition of MPAA ratings for different genres"),
- plotgrid.args = list(nrow = 2)
+ palette = "default_ucscgb" # choosing a different color palette
)
```
-
+
### Summary of tests
@@ -1095,29 +1025,16 @@ function-
# setup
set.seed(123)
-# smaller dataset
-df <-
- dplyr::filter(
- .data = forcats::gss_cat,
- race %in% c("Black", "White"),
- relig %in% c("Protestant", "Catholic", "None"),
- !partyid %in% c("No answer", "Don't know", "Other party")
- )
-
# plot
grouped_ggbarstats(
- data = df,
- x = relig,
- y = partyid,
- grouping.var = race,
- label = "both",
- xlab = "Party affiliation",
+ data = mtcars,
+ x = am,
+ y = cyl,
+ grouping.var = vs,
package = "wesanderson",
palette = "Darjeeling2",
ggtheme = ggthemes::theme_tufte(base_size = 12),
- ggstatsplot.layer = FALSE,
- annotation.args = list(title = "Race, religion, and political affiliation"),
- plotgrid.args = list(nrow = 2)
+ ggstatsplot.layer = FALSE
)
```
@@ -1381,8 +1298,7 @@ different aspects of statistical analyses:
The `statsExpressions` package forms the statistical backend that
processes data and creates expressions containing results from
-statistical tests and are by default displayed in as plot **subtitle**
-and **caption**.
+statistical tests.
For more exhaustive documentation for this package, see:
📝 Defaults return
✅ raw data + distributions
✅ descriptive statistics
✅ inferential statistics
✅ effect size + CIs
✅ pairwise comparisons
✅ Bayesian hypothesis-testing
✅ Bayesian estimation
A number of other arguments can be specified to make this plot even more informative or change some of the default options.
+A number of other arguments can be specified to make this plot even more informative or change some of the default options. Additionally, there is also a grouped_ variant of this function that makes it easy to repeat the same operation across a single grouping variable:
# for reproducibility
set.seed(123)
-library(ggplot2)
-
-# plot
-ggbetweenstats(
- data = ToothGrowth,
- x = supp,
- y = len,
- type = "r", # robust statistics
- k = 3, # number of decimal places for statistical results
- xlab = "Supplement type", # label for the x-axis variable
- ylab = "Tooth length", # label for the y-axis variable
- title = "The Effect of Vitamin C on Tooth Growth", # title text for the plot
- ggtheme = ggthemes::theme_fivethirtyeight(), # choosing a different theme
- ggstatsplot.layer = FALSE, # turn off `ggstatsplot` theme layer
- package = "wesanderson", # package from which color palette is to be taken
- palette = "Darjeeling1" # choosing a different color palette
-)
Additionally, there is also a grouped_ variant of this function that makes it easy to repeat the same operation across a single grouping variable:
-# for reproducibility
-set.seed(123)
# plot
grouped_ggbetweenstats(
- data = dplyr::filter(
- .data = movies_long,
- genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy")
- ),
+ data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")),
x = mpaa,
y = length,
grouping.var = genre, # grouping variable
@@ -584,10 +559,10 @@
caption = substitute(paste(italic("Source"), ": IMDb (Internet Movie Database)")),
palette = "default_jama",
package = "ggsci",
- plotgrid.args = list(nrow = 2),
+ plotgrid.args = list(nrow = 1),
annotation.args = list(title = "Differences in movie length by mpaa ratings for different genres")
)
Note here that the function can be used to tag outliers!
ggwithinstats
ggbetweenstats function has an identical twin function ggwithinstats for repeated measures designs that behaves in the same fashion with a few minor tweaks introduced to properly visualize the repeated measures design. As can be seen from an example below, the only difference between the plot structure is that now the group means are connected by paths to highlight the fact that these data are paired with each other.
+# for reproducibility and data set.seed(123) library(WRS2) # for data @@ -873,7 +848,7 @@
As with the
-ggbetweenstats, this function also has agrouped_variant that makes repeating the same analysis across a single grouping variable quicker. We will see an example with only repeated measurements-+# common setup set.seed(123) @@ -1124,7 +1099,7 @@
gghistostatsTo visualize the distribution of a single variable and check if its mean is significantly different from a specified value with a one-sample test,
-gghistostatscan be used.+# for reproducibility set.seed(123) @@ -1143,16 +1118,13 @@
📝 Defaults return
✅ counts + proportion for bins
✅ descriptive statistics
✅ inferential statistics
✅ effect size + CIs
✅ Bayesian hypothesis-testing
✅ Bayesian estimationThere is also a
-grouped_variant of this function that makes it easy to repeat the same operation across a single grouping variable:+# for reproducibility set.seed(123) # plot grouped_gghistostats( - data = dplyr::filter( - .data = movies_long, - genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy") - ), + data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")), x = budget, test.value = 50, type = "nonparametric", @@ -1163,7 +1135,7 @@ggtheme = ggthemes::theme_tufte(), # modify the defaults from `ggstatsplot` for each plot ggplot.component = ggplot2::labs(caption = "Source: IMDB.com"), - plotgrid.args = list(nrow = 2), + plotgrid.args = list(nrow = 1), annotation.args = list(title = "Movies budgets for different genres") )
@@ -1285,7 +1257,7 @@
ggdotplotstatsThis function is similar to
-gghistostats, but is intended to be used when the numeric variable also has a label.+# for reproducibility set.seed(123) @@ -1309,7 +1281,7 @@
📝 Defaults return
✅ descriptives (mean + sample size)
✅ inferential statistics
✅ effect size + CIs
✅ Bayesian hypothesis-testing
✅ Bayesian estimationAs with the rest of the functions in this package, there is also a
-grouped_variant of this function to facilitate looping the same operation for all levels of a single grouping variable.+# for reproducibility set.seed(123) @@ -1338,7 +1310,7 @@
ggscatterstatsThis function creates a scatterplot with marginal distributions overlaid on the axes (from
-ggExtra::ggMarginal) and results from statistical tests in the subtitle:+ggscatterstats( data = ggplot2::msleep, x = sleep_rem, @@ -1359,13 +1331,13 @@
densigram (density + histogram) Number of other arguments can be specified to modify this basic plot-
-+# for reproducibility set.seed(123) # plot ggscatterstats( - data = dplyr::filter(.data = movies_long, genre == "Action"), + data = dplyr::filter(movies_long, genre == "Action"), x = budget, y = rating, type = "robust", # type of test that needs to be run @@ -1383,16 +1355,13 @@)
Additionally, there is also a
-grouped_variant of this function that makes it easy to repeat the same operation across a single grouping variable. Also, note that, as opposed to the other functions, this function does not return aggplotobject and any modification you want to make can be made in advance usingggplot.componentargument (available for all functions, but especially useful here):+# for reproducibility set.seed(123) # plot grouped_ggscatterstats( - data = dplyr::filter( - .data = movies_long, - genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy") - ), + data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")), x = rating, y = length, grouping.var = genre, # grouping variable @@ -1403,8 +1372,8 @@ggplot.component = list( ggplot2::scale_x_continuous(breaks = seq(2, 9, 1), limits = (c(2, 9))) ), - plotgrid.args = list(nrow = 2), - annotation.args = list(title = "Relationship between movie length by IMDB ratings for different genres") + plotgrid.args = list(nrow = 1), + annotation.args = list(title = "Relationship between movie length and IMDB ratings") )
@@ -1459,7 +1428,7 @@
ggcorrmat-
ggcorrmatmakes a correlalogram (a matrix of correlation coefficients) with minimal amount of code. Just sticking to the defaults itself produces publication-ready correlation matrices. But, for the sake of exploring the available options, let’s change some of the defaults. For example, multiple aesthetics-related arguments can be modified to change the appearance of the correlation matrix.++#> $ title <chr> "'Til There Was You", "10 Things I Hate About You", "100 Mil… +#> $ year <int> 1997, 1999, 2002, 2004, 1999, 2001, 1972, 2003, 1999, 2000, … +#> $ length <int> 113, 97, 98, 98, 102, 120, 180, 107, 101, 99, 129, 124, 93, … +#> $ budget <dbl> 23.0, 16.0, 1.1, 37.0, 85.0, 42.0, 4.0, 76.0, 6.0, 26.0, 12.… +#> $ rating <dbl> 4.8, 6.7, 5.6, 6.4, 6.1, 6.1, 7.3, 5.1, 5.4, 2.5, 7.6, 8.0, … +#> $ votes <int> 799, 19095, 181, 7859, 14344, 10866, 1754, 9556, 4514, 2023,… +#> $ mpaa <fct> PG-13, PG-13, R, PG-13, R, R, PG, PG-13, R, R, R, R, R, R, P… +#> $ Action <int> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, … +#> $ Animation <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … +#> $ Comedy <int> 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, … +#> $ Drama <int> 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, … +#> $ Romance <int> 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, … +#> $ NumGenre <int> 2, 2, 1, 3, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 2, 3, 2, 2, 1, …# for reproducibility set.seed(123) @@ -1475,16 +1444,13 @@
✅ effect size + significance
✅ careful handling ofNAsIf there are
NAs present in the selected variables, the legend will display minimum, median, and maximum number of pairs used for correlation tests.There is also a
-grouped_variant of this function that makes it easy to repeat the same operation across a single grouping variable:++#> $ title <chr> "Shawshank Redemption, The", "Lord of the Rings: The Return of … +#> $ year <int> 1994, 2003, 2001, 2002, 1994, 1993, 1977, 1980, 1968, 2002, 196… +#> $ length <int> 142, 251, 208, 223, 168, 195, 125, 129, 158, 135, 93, 113, 108,… +#> $ budget <dbl> 25.0, 94.0, 93.0, 94.0, 8.0, 25.0, 11.0, 18.0, 5.0, 3.3, 1.8, 5… +#> $ rating <dbl> 9.1, 9.0, 8.8, 8.8, 8.8, 8.8, 8.8, 8.8, 8.7, 8.7, 8.7, 8.7, 8.6… +#> $ votes <int> 149494, 103631, 157608, 114797, 132745, 97667, 134640, 103706, … +#> $ mpaa <fct> R, PG-13, PG-13, PG-13, R, R, PG, PG, PG-13, R, PG, R, R, R, R,… +#> $ genre <fct> Drama, Action, Action, Action, Drama, Drama, Action, Action, Dr…# for reproducibility set.seed(123) # plot grouped_ggcorrmat( - data = dplyr::filter( - .data = movies_long, - genre %in% c("Action", "Action Comedy", "Action Drama", "Comedy") - ), + data = dplyr::filter(movies_long, genre %in% c("Action", "Comedy")), type = "robust", # correlation method colors = c("#cbac43", "white", "#550000"), grouping.var = genre, # grouping variable @@ -1492,7 +1458,7 @@)
You can also get a dataframe containing all relevant details from the statistical tests:
-+# setup set.seed(123) @@ -1555,7 +1521,7 @@#> 14 Bayesian Pearson correlation 83 #> 15 Bayesian Pearson correlation 56
Additionally, partial correlation are also supported:
-++#> $ id <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1… +#> $ Species <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, seto… +#> $ condition <fct> Sepal.Length, Sepal.Length, Sepal.Length, Sepal.Length, Sepa… +#> $ attribute <fct> Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepa… +#> $ measure <fct> Length, Length, Length, Length, Length, Length, Length, Leng… +#> $ value <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, …# setup set.seed(123) @@ -1676,7 +1642,7 @@
This function creates a pie chart for categorical or nominal variables with results from contingency table analysis (Pearson’s chi-squared test for between-subjects design and McNemar’s chi-squared test for within-subjects design) included in the subtitle of the plot. If only one categorical variable is entered, results from one-sample proportion test (i.e., a chi-squared goodness of fit test) will be displayed as a subtitle.
To study an interaction between two categorical variables:
-++# for reproducibility set.seed(123) @@ -1685,6 +1651,8 @@data = mtcars, x = am, y = cyl, + package = "wesanderson", + palette = "Royal1", title = "Dataset: Motor Trend Car Road Tests", # title for the plot legend.title = "Transmission", # title for the legend caption = substitute(paste(italic("Source"), ": 1974 Motor Trend US magazine")) @@ -1692,50 +1660,21 @@
📝 Defaults return
✅ descriptives (frequency + %s)
-
✅ inferential statistics
✅ effect size + CIs
✅ Goodness-of-fit tests
✅ Bayesian hypothesis-testing
✅ Bayesian estimationIn case of repeated measures designs, setting
-paired = TRUEwill produce results from McNemar’s chi-squared test---# for reproducibility -set.seed(123) - -# data -df_paired <- - data.frame( - "before" = c("Approve", "Approve", "Disapprove", "Disapprove"), - "after" = c("Approve", "Disapprove", "Approve", "Disapprove"), - counts = c(794, 150, 86, 570), - check.names = FALSE - ) - -# plot -ggpiestats( - data = df_paired, - x = before, - y = after, - counts = counts, - title = "Survey results before and after the intervention", - label = "both", - paired = TRUE, # within-subjects design - package = "wesanderson", - palette = "Royal1" -)-
Additionally, there is also a
-grouped_variant of this function that makes it easy to repeat the same operation across a single grouping variable. Following example is a case where the theoretical question is about proportions for different levels of a single nominal variable:+There is also a
+grouped_variant of this function that makes it easy to repeat the same operation across a single grouping variable. Following example is a case where the theoretical question is about proportions for different levels of a single nominal variable:-# for reproducibility set.seed(123) # plot grouped_ggpiestats( - data = movies_long, - x = genre, - grouping.var = mpaa, # grouping variable + data = mtcars, + x = cyl, + grouping.var = am, # grouping variable label.repel = TRUE, # repel labels (helpful for overlapping labels) package = "ggsci", # package from which color palette is to be taken - palette = "default_ucscgb", # choosing a different color palette - annotation.args = list(title = "Composition of MPAA ratings for different genres"), - plotgrid.args = list(nrow = 2) + palette = "default_ucscgb" # choosing a different color palette )+
Summary of tests
@@ -1818,7 +1757,7 @@
In case you are not a fan of pie charts (for very good reasons), you can alternatively use
ggbarstatsfunction which has a similar syntax.N.B. The p-values from one-sample proportion test are displayed on top of each bar.
-++#> $ subject <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1… +#> $ gender <fct> Female, Female, Female, Female, Female, Female, Female, Fema… +#> $ region <fct> North America, North America, Europe, North America, North A… +#> $ education <fct> some, advance, college, college, some, some, some, high, hig… +#> $ ldlf <dbl> 6.0, 10.0, 5.0, 6.0, 3.0, 2.0, 10.0, 10.0, 9.5, 8.5, 0.0, 9.… +#> $ ldhf <dbl> 6.0, NA, 10.0, 9.0, 6.5, 0.5, 10.0, 10.0, 9.5, 10.0, 2.5, 7.… +#> $ hdlf <dbl> 9.0, 10.0, 10.0, 6.0, 5.5, 7.5, 10.0, 9.0, 6.0, 7.0, 0.0, 8.… +#> $ hdhf <dbl> 10.0, 10.0, 10.0, 9.0, 8.5, 3.0, 10.0, 10.0, 10.0, NA, 0.0, …# for reproducibility set.seed(123) library(ggplot2) @@ -1839,33 +1778,20 @@
📝 Defaults return
✅ descriptives (frequency + %s)
✅ inferential statistics
✅ effect size + CIs
✅ Goodness-of-fit tests
✅ Bayesian hypothesis-testing
✅ Bayesian estimationAnd, needless to say, there is also a
-grouped_variant of this function-++#> $ subject <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1… +#> $ gender <fct> Female, Female, Female, Female, Female, Female, Female, Fema… +#> $ region <fct> North America, North America, Europe, North America, North A… +#> $ education <fct> some, advance, college, college, some, some, some, high, hig… +#> $ condition <chr> "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDL… +#> $ desire <dbl> 6.0, 10.0, 5.0, 6.0, 3.0, 2.0, 10.0, 10.0, 9.5, 8.5, 0.0, 9.…# setup set.seed(123) -# smaller dataset -df <- - dplyr::filter( - .data = forcats::gss_cat, - race %in% c("Black", "White"), - relig %in% c("Protestant", "Catholic", "None"), - !partyid %in% c("No answer", "Don't know", "Other party") - ) - # plot grouped_ggbarstats( - data = df, - x = relig, - y = partyid, - grouping.var = race, - label = "both", - xlab = "Party affiliation", + data = mtcars, + x = am, + y = cyl, + grouping.var = vs, package = "wesanderson", palette = "Darjeeling2", ggtheme = ggthemes::theme_tufte(base_size = 12), - ggstatsplot.layer = FALSE, - annotation.args = list(title = "Race, religion, and political affiliation"), - plotgrid.args = list(nrow = 2) + ggstatsplot.layer = FALSE )
@@ -1886,7 +1812,7 @@
The caption will contain diagnostic information, if available, about models that can be useful for model selection: The smaller the Akaike’s Information Criterion (AIC) and the Bayesian Information Criterion (BIC) values, the “better” the model is.
- The output of this function will be a
ggplot2object and, thus, it can be further modified (e.g., change themes, etc.) withggplot2functions.++#> $ id <dbl> 1, 6, 7, 8, 9, 10, 12, 14, 15, 17, 20, 22, 28, 31, 34, 35, 36… +#> $ order <chr> "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "… +#> $ modality <chr> "text", "text", "text", "text", "text", "text", "text", "text… +#> $ score <dbl> 0.25, 1.00, 1.00, 1.00, 0.50, 0.75, 1.00, 1.00, 0.75, 0.00, 0…# for reproducibility set.seed(123) @@ -1899,7 +1825,7 @@
📝 Defaults return
✅ inferential statistics
✅ estimate + CIs
✅ model summary (AIC + BIC)This default plot can be further modified to one’s liking with additional arguments (also, let’s use a different model now):
-++#> $ id <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18… +#> $ Class <fct> 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3… +#> $ Sex <fct> Male, Male, Male, Male, Male, Male, Male, Male, Male, Male, M… +#> $ Age <fct> Child, Child, Child, Child, Child, Child, Child, Child, Child… +#> $ Survived <fct> No, No, No, No, No, No, No, No, No, No, No, No, No, No, No, N…# for reproducibility set.seed(123) @@ -1985,7 +1911,7 @@Using
ggstatsplotstatistical details with custom plotsSometimes you may not like the default plots produced by
ggstatsplot. In such cases, you can use other custom plots (fromggplot2or other plotting packages) and still useggstatsplotfunctions to display results from relevant statistical test.For example, in the following chunk, we will create plot (ridgeplot) using
-ggridgespackage and useggstatsplotfunction for extracting results.@@ -2090,7 +2016,7 @@+# loading the needed libraries set.seed(123) library(ggridges) @@ -2063,7 +1989,7 @@
-
statsExpressionsThe
+statsExpressionspackage forms the statistical backend that processes data and creates expressions containing results from statistical tests and are by default displayed in as plot subtitle and caption.The
statsExpressionspackage forms the statistical backend that processes data and creates expressions containing results from statistical tests.For more exhaustive documentation for this package, see: https://indrajeetpatil.github.io/statsExpressions/
@@ -2077,7 +2003,7 @@
-
ipmiscThe
+ipmiscpackage contains some of the data wrangling/cleaning functions and a few other miscellaneous functions.The
ipmiscpackage contains the data wrangling/cleaning functions and a few other miscellaneous functions.For more exhaustive documentation for this package, see: https://indrajeetpatil.github.io/ipmisc/
Acknowledgments
I would like to thank all the contributors to
-ggstatsplotwho pointed out bugs or requested features I hadn’t considered. I would especially like to thank other package developers (especially Daniel Lüdecke, Dominique Makowski, Mattan S. Ben-Shachar, Patrick Mair, Salvatore Mangiafico, etc.) who have patiently and diligently answered my relentless number of questions and added feature requests I wanted. I also want to thank Chuck Powell for his initial contributions to the package.The hexsticker was generously designed by Sarah Otterstetter (Max Planck Institute for Human Development, Berlin). This package has also benefited from the larger
+rstatscommunity on Twitter and StackOverflow.The hexsticker was generously designed by Sarah Otterstetter (Max Planck Institute for Human Development, Berlin). This package has also benefited from the larger
rstatscommunity on Twitter andStackOverflow.Thanks are also due to my postdoc advisers (Mina Cikara and Fiery Cushman at Harvard University; Iyad Rahwan at Max Planck Institute for Human Development) who patiently supported me spending hundreds of hours working on this package rather than what I was paid to do. 😄
diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 8243d066f..7a35d21d8 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -1,6 +1,6 @@ -pandoc: '2.13' +pandoc: 2.11.4 pkgdown: 1.6.1.9001 -pkgdown_sha: ddafb4ac3eff2ec4e5988b6b13bc4585e9df186c +pkgdown_sha: 3dd1a1ad7740977491241c89eee15d9b58e75866 articles: additional: additional.html web_only/benchmarking: benchmarking.html @@ -21,7 +21,7 @@ articles: web_only/purrr_examples: purrr_examples.html web_only/session_info: session_info.html web_only/theme_ggstatsplot: theme_ggstatsplot.html -last_built: 2021-04-06T11:38Z +last_built: 2021-04-12T17:40Z urls: reference: https://indrajeetpatil.github.io/ggstatsplot/reference article: https://indrajeetpatil.github.io/ggstatsplot/articles diff --git a/docs/reference/Rplot001.png b/docs/reference/Rplot001.png index a0cb562b9..17a358060 100644 Binary files a/docs/reference/Rplot001.png and b/docs/reference/Rplot001.png differ diff --git a/docs/reference/Titanic_full.html b/docs/reference/Titanic_full.html index a849332f1..074a2e613 100644 --- a/docs/reference/Titanic_full.html +++ b/docs/reference/Titanic_full.html @@ -255,11 +255,11 @@Examp #> 6 6 3rd Male Child No
#> Rows: 2,201 #> Columns: 5 -#> $ id <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18~ -#> $ Class <fct> 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3rd, 3~ -#> $ Sex <fct> Male, Male, Male, Male, Male, Male, Male, Male, Male, Male, M~ -#> $ Age <fct> Child, Child, Child, Child, Child, Child, Child, Child, Child~ -#> $ Survived <fct> No, No, No, No, No, No, No, No, No, No, No, No, No, No, No, N~#> Rows: 68 #> Columns: 4 -#> $ id <dbl> 1, 6, 7, 8, 9, 10, 12, 14, 15, 17, 20, 22, 28, 31, 34, 35, 36~ -#> $ order <chr> "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "0", "~ -#> $ modality <chr> "text", "text", "text", "text", "text", "text", "text", "text~ -#> $ score <dbl> 0.25, 1.00, 1.00, 1.00, 0.50, 0.75, 1.00, 1.00, 0.75, 0.00, 0~#> Rows: 372 #> Columns: 6 -#> $ subject <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1~ -#> $ gender <fct> Female, Female, Female, Female, Female, Female, Female, Fema~ -#> $ region <fct> North America, North America, Europe, North America, North A~ -#> $ education <fct> some, advance, college, college, some, some, some, high, hig~ -#> $ condition <chr> "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDLF", "LDL~ -#> $ desire <dbl> 6.0, 10.0, 5.0, 6.0, 3.0, 2.0, 10.0, 10.0, 9.5, 8.5, 0.0, 9.~#> Rows: 93 #> Columns: 8 -#> $ subject <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1~ -#> $ gender <fct> Female, Female, Female, Female, Female, Female, Female, Fema~ -#> $ region <fct> North America, North America, Europe, North America, North A~ -#> $ education <fct> some, advance, college, college, some, some, some, high, hig~ -#> $ ldlf <dbl> 6.0, 10.0, 5.0, 6.0, 3.0, 2.0, 10.0, 10.0, 9.5, 8.5, 0.0, 9.~ -#> $ ldhf <dbl> 6.0, NA, 10.0, 9.0, 6.5, 0.5, 10.0, 10.0, 9.5, 10.0, 2.5, 7.~ -#> $ hdlf <dbl> 9.0, 10.0, 10.0, 6.0, 5.5, 7.5, 10.0, 9.0, 6.0, 7.0, 0.0, 8.~ -#> $ hdhf <dbl> 10.0, 10.0, 10.0, 9.0, 8.5, 3.0, 10.0, 10.0, 10.0, NA, 0.0, ~#> # A tibble: 15 x 11 -#> parameter1 parameter2 estimate conf.level conf.low conf.high statistic +#> parameter1 parameter2 estimate conf.level conf.low conf.high statistic #> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> -#> 1 sleep_total sleep_rem 0.314 0.95 -0.0520 0.606 1.75 -#> 2 sleep_total sleep_cycle -0.0225 0.95 -0.380 0.341 -0.119 -#> 3 sleep_total awake -1 0.95 -1 -1 -Inf -#> 4 sleep_total brainwt -0.0970 0.95 -0.442 0.273 -0.516 -#> 5 sleep_total bodywt -0.179 0.95 -0.506 0.194 -0.961 -#> 6 sleep_rem sleep_cycle -0.0766 0.95 -0.425 0.292 -0.407 -#> 7 sleep_rem awake 0.0560 0.95 -0.311 0.408 0.297 -#> 8 sleep_rem brainwt 0.0857 0.95 -0.283 0.433 0.455 -#> 9 sleep_rem bodywt -0.0341 0.95 -0.390 0.330 -0.181 -#> 10 sleep_cycle awake -0.00479 0.95 -0.364 0.356 -0.0253 -#> 11 sleep_cycle brainwt 0.801 0.95 0.620 0.901 7.08 -#> 12 sleep_cycle bodywt -0.0949 0.95 -0.440 0.275 -0.505 -#> 13 awake brainwt -0.0957 0.95 -0.441 0.274 -0.509 -#> 14 awake bodywt -0.448 0.95 -0.696 -0.104 -2.65 -#> 15 brainwt bodywt 0.252 0.95 -0.119 0.561 1.38 -#> # … with 4 more variables: df.error <int>, p.value <dbl>, method <chr>, -#> # n.obs <int># } +#> 1 sleep_total sleep_rem 0.314 0.95 -0.0520 0.606 1.75 +#> 2 sleep_total sleep_cycle -0.0225 0.95 -0.380 0.341 -0.119 +#> 3 sleep_total awake -1 0.95 -1 -1 -Inf +#> 4 sleep_total brainwt -0.0970 0.95 -0.442 0.273 -0.516 +#> 5 sleep_total bodywt -0.179 0.95 -0.506 0.194 -0.961 +#> 6 sleep_rem sleep_cycle -0.0766 0.95 -0.425 0.292 -0.407 +#> 7 sleep_rem awake 0.0560 0.95 -0.311 0.408 0.297 +#> 8 sleep_rem brainwt 0.0857 0.95 -0.283 0.433 0.455 +#> 9 sleep_rem bodywt -0.0341 0.95 -0.390 0.330 -0.181 +#> 10 sleep_cycle awake -0.00479 0.95 -0.364 0.356 -0.0253 +#> 11 sleep_cycle brainwt 0.801 0.95 0.620 0.901 7.08 +#> 12 sleep_cycle bodywt -0.0949 0.95 -0.440 0.275 -0.505 +#> 13 awake brainwt -0.0957 0.95 -0.441 0.274 -0.509 +#> 14 awake bodywt -0.448 0.95 -0.696 -0.104 -2.65 +#> 15 brainwt bodywt 0.252 0.95 -0.119 0.561 1.38 +#> df.error p.value method n.obs +#> <int> <dbl> <chr> <int> +#> 1 28 1 Pearson correlation 30 +#> 2 28 1 Pearson correlation 30 +#> 3 28 0 Pearson correlation 30 +#> 4 28 1 Pearson correlation 30 +#> 5 28 1 Pearson correlation 30 +#> 6 28 1 Pearson correlation 30 +#> 7 28 1 Pearson correlation 30 +#> 8 28 1 Pearson correlation 30 +#> 9 28 1 Pearson correlation 30 +#> 10 28 1 Pearson correlation 30 +#> 11 28 0.00000148 Pearson correlation 30 +#> 12 28 1 Pearson correlation 30 +#> 13 28 1 Pearson correlation 30 +#> 14 28 0.170 Pearson correlation 30 +#> 15 28 1 Pearson correlation 30# }#>#>#> +#>#> +#> +#>#> Warning: Series not converged.#> Warning: Series not converged.#> Warning: Series not converged.#> Warning: Series not converged.#> # A tibble: 60 x 15 -#> vore parameter1 parameter2 estimate conf.level conf.low conf.high pd +#> vore parameter1 parameter2 estimate conf.level conf.low conf.high pd #> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> -#> 1 carni sleep_total sleep_rem 0.845 0.95 0.641 0.961 1 -#> 2 carni sleep_total sleep_cycle 0.204 0.95 -0.351 0.764 0.698 -#> 3 carni sleep_total awake -1.00 0.95 -1.00 -1.00 1 -#> 4 carni sleep_total brainwt -0.382 0.95 -0.759 0.0549 0.895 -#> 5 carni sleep_total bodywt -0.379 0.95 -0.662 -0.0654 0.960 -#> 6 carni sleep_rem sleep_cycle 0.0548 0.95 -0.534 0.587 0.562 -#> 7 carni sleep_rem awake -0.848 0.95 -0.962 -0.678 1 -#> 8 carni sleep_rem brainwt -0.308 0.95 -0.760 0.252 0.804 -#> 9 carni sleep_rem bodywt -0.371 0.95 -0.716 0.0694 0.899 -#> 10 carni sleep_cycle awake -0.205 0.95 -0.754 0.373 0.690 -#> # … with 50 more rows, and 7 more variables: rope.percentage <dbl>, -#> # prior.distribution <chr>, prior.location <dbl>, prior.scale <dbl>, -#> # bayes.factor <dbl>, method <chr>, n.obs <int># } +#> 1 carni sleep_total sleep_rem 0.845 0.95 0.641 0.961 1 +#> 2 carni sleep_total sleep_cycle 0.204 0.95 -0.351 0.764 0.698 +#> 3 carni sleep_total awake -1.00 0.95 -1.00 -1.00 1 +#> 4 carni sleep_total brainwt -0.382 0.95 -0.759 0.0549 0.895 +#> 5 carni sleep_total bodywt -0.379 0.95 -0.662 -0.0654 0.960 +#> 6 carni sleep_rem sleep_cycle 0.0548 0.95 -0.534 0.587 0.562 +#> 7 carni sleep_rem awake -0.848 0.95 -0.962 -0.678 1 +#> 8 carni sleep_rem brainwt -0.308 0.95 -0.760 0.252 0.804 +#> 9 carni sleep_rem bodywt -0.371 0.95 -0.716 0.0694 0.899 +#> 10 carni sleep_cycle awake -0.205 0.95 -0.754 0.373 0.690 +#> rope.percentage prior.distribution prior.location prior.scale bayes.factor +#> <dbl> <chr> <dbl> <dbl> <dbl> +#> 1 0 beta 1.41 1.41 112. +#> 2 0.168 beta 1.41 1.41 0.714 +#> 3 0 beta 1.41 1.41 NA +#> 4 0.116 beta 1.41 1.41 1.13 +#> 5 0.078 beta 1.41 1.41 1.72 +#> 6 0.206 beta 1.41 1.41 0.621 +#> 7 0.0118 beta 1.41 1.41 112. +#> 8 0.136 beta 1.41 1.41 0.848 +#> 9 0.124 beta 1.41 1.41 1.03 +#> 10 0.165 beta 1.41 1.41 0.714 +#> method n.obs +#> <chr> <int> +#> 1 Bayesian Pearson correlation 10 +#> 2 Bayesian Pearson correlation 5 +#> 3 Bayesian Pearson correlation 19 +#> 4 Bayesian Pearson correlation 9 +#> 5 Bayesian Pearson correlation 19 +#> 6 Bayesian Pearson correlation 5 +#> 7 Bayesian Pearson correlation 10 +#> 8 Bayesian Pearson correlation 6 +#> 9 Bayesian Pearson correlation 10 +#> 10 Bayesian Pearson correlation 5 +#> # … with 50 more rows# }#> Rows: 600 #> Columns: 6 -#> $ id <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1~ -#> $ Species <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, seto~ -#> $ condition <fct> Sepal.Length, Sepal.Length, Sepal.Length, Sepal.Length, Sepa~ -#> $ attribute <fct> Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepal, Sepa~ -#> $ measure <fct> Length, Length, Length, Length, Length, Length, Length, Leng~ -#> $ value <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, ~#> Rows: 1,579 #> Columns: 8 -#> $ title <chr> "Shawshank Redemption, The", "Lord of the Rings: The Return of ~ -#> $ year <int> 1994, 2003, 2001, 2002, 1994, 1993, 1977, 1980, 1968, 2002, 196~ -#> $ length <int> 142, 251, 208, 223, 168, 195, 125, 129, 158, 135, 93, 113, 108,~ -#> $ budget <dbl> 25.0, 94.0, 93.0, 94.0, 8.0, 25.0, 11.0, 18.0, 5.0, 3.3, 1.8, 5~ -#> $ rating <dbl> 9.1, 9.0, 8.8, 8.8, 8.8, 8.8, 8.8, 8.8, 8.7, 8.7, 8.7, 8.7, 8.6~ -#> $ votes <int> 149494, 103631, 157608, 114797, 132745, 97667, 134640, 103706, ~ -#> $ mpaa <fct> R, PG-13, PG-13, PG-13, R, R, PG, PG, PG-13, R, PG, R, R, R, R,~ -#> $ genre <fct> Drama, Action, Action, Action, Drama, Drama, Action, Action, Dr~#> Rows: 1,579 #> Columns: 13 -#> $ title <chr> "'Til There Was You", "10 Things I Hate About You", "100 Mil~ -#> $ year <int> 1997, 1999, 2002, 2004, 1999, 2001, 1972, 2003, 1999, 2000, ~ -#> $ length <int> 113, 97, 98, 98, 102, 120, 180, 107, 101, 99, 129, 124, 93, ~ -#> $ budget <dbl> 23.0, 16.0, 1.1, 37.0, 85.0, 42.0, 4.0, 76.0, 6.0, 26.0, 12.~ -#> $ rating <dbl> 4.8, 6.7, 5.6, 6.4, 6.1, 6.1, 7.3, 5.1, 5.4, 2.5, 7.6, 8.0, ~ -#> $ votes <int> 799, 19095, 181, 7859, 14344, 10866, 1754, 9556, 4514, 2023,~ -#> $ mpaa <fct> PG-13, PG-13, R, PG-13, R, R, PG, PG-13, R, R, R, R, R, R, P~ -#> $ Action <int> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, ~ -#> $ Animation <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ~ -#> $ Comedy <int> 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, ~ -#> $ Drama <int> 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, ~ -#> $ Romance <int> 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, ~ -#> $ NumGenre <int> 2, 2, 1, 3, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 2, 3, 2, 2, 1, ~
