fix failing checks

easystats · Oct 4, 2023 · 6d8d3bb · 6d8d3bb
1 parent 273be72
commit 6d8d3bb
Show file tree

Hide file tree

Showing 2 changed files with 38 additions and 22 deletions.
diff --git a/inst/WORDLIST b/inst/WORDLIST
@@ -9,6 +9,7 @@ Ankerst
 Archimbaud
 Arel
 Asq
+BCI
 BFBayesFactor
 BMJ
 Baayen
@@ -75,6 +76,7 @@ Gazen
 Gelman
 Gnanadesikan
 Guilford
+HDI
 HJ
 Hastie
 Herron
@@ -110,10 +112,10 @@ Killeen
 Kliegl
 Kristensen
 Kullback
-Lakens
 LOF
 LOGLOSS
 LOOIC
+Lakens
 Laniado
 Leibler
 Lemeshow
@@ -123,6 +125,7 @@ Leys
 Lillo
 Liu
 Lomax
+MADs
 MSA
 Maddala
 Magee
@@ -148,6 +151,7 @@ Nakagawa's
 Nordhausen
 Normed
 ORCID
+OSF
 Olkin
 PNFI
 Pek
@@ -210,6 +214,7 @@ WAIC
 WMK
 Weisberg
 Windmeijer
+Winsorization
 Witten
 Xu
 YL
@@ -237,6 +242,7 @@ brmsfit
 cauchy
 clusterable
 concurvity
+datawizard
 dbscan
 der
 detrend
@@ -252,20 +258,17 @@ fpsyg
 gam
 geoms
 ggplot
-github
 gjo
 glm
 glmmTMB
 glmrob
 grey
 heteroskedasticity
-homoskedasticity
 homoscedasticity
+homoskedasticity
 https
 intra
 intraclass
-io
-ize
 joss
 kmeans
 lavaan
@@ -285,18 +288,22 @@ models’
 multicollinearity
 multimodel
 multiresponse
+multivariable
 nd
 nonnest
 overfitted
 patilindrajeets
 poisson
 preprint
+priori
 pscl
 quared
 quartile
 quartiles
 rOpenSci
+recoding
 rempsyc
+reproducibility
 rescaling
 rma
 rmarkdown
@@ -308,6 +315,7 @@ se
 smicd
 sphericity
 strengejacke
+suboptimal
 subscale
 subscales
 theoreritcal
@@ -317,5 +325,8 @@ und
 underfitted
 underfitting
 visualisation
+winsorization
+winsorize
+winsorized
 xy
 youtube
diff --git a/vignettes/check_outliers.Rmd b/vignettes/check_outliers.Rmd
@@ -8,7 +8,7 @@ output:
 bibliography: paper.bib
 vignette: >
   \usepackage[utf8]{inputenc}
-  %\VignetteIndexEntry{Checking model assumption - linear models}
+  %\VignetteIndexEntry{Checking outliers with *performance*}
   %\VignetteEngine{knitr::rmarkdown}
 editor_options: 
   chunk_output_type: console
@@ -110,10 +110,10 @@ plot(outliers)
 
 ```{r univariate_implicit, fig.cap = "Visual depiction of outliers using the robust z-score method. The distance represents an aggregate score for variables mpg, cyl, disp, and hp.", echo=FALSE}
 library(see)
-plot(outliers) + 
+plot(outliers) +
   ggplot2::theme(axis.text.x = ggplot2::element_text(
     angle = 45, size = 7
-))
+  ))
 ```
 
 Other univariate methods are available, such as using the interquartile range (IQR), or based on different intervals, such as the Highest Density Interval (HDI) or the Bias Corrected and Accelerated Interval (BCI). These methods are documented and described in the function's [help page](<https://easystats.github.io/performance/reference/check_outliers.html>).
@@ -140,10 +140,10 @@ plot(outliers)
 ```
 
 ```{r multivariate_implicit, fig.cap = "Visual depiction of outliers using the Minimum Covariance Determinant (MCD) method, a robust version of the Mahalanobis distance. The distance represents the MCD scores for variables mpg, cyl, disp, and hp.", echo=FALSE}
-plot(outliers) + 
+plot(outliers) +
   ggplot2::theme(axis.text.x = ggplot2::element_text(
     angle = 45, size = 7
-))
+  ))
 ```
 
 Other multivariate methods are available, such as another type of robust Mahalanobis distance that in this case relies on an orthogonalized Gnanadesikan-Kettenring pairwise estimator [@gnanadesikan1972robust]. These methods are documented and described in the function's [help page](https://easystats.github.io/performance/reference/check_outliers.html).
@@ -169,21 +169,26 @@ Table 1 below summarizes which methods to use in which cases, and with what thre
 ```{r, echo=FALSE}
 df <- data.frame(
   `Statistical Test` = c(
-    "Supported regression model", 
-    "Structural Equation Modeling (or other unsupported model)", 
-    "Simple test with few variables (*t* test, correlation, etc.)"),
+    "Supported regression model",
+    "Structural Equation Modeling (or other unsupported model)",
+    "Simple test with few variables (*t* test, correlation, etc.)"
+  ),
   `Diagnosis Method` = c(
-    "**Model-based**: Cook (or Pareto for Bayesian models)", 
-    "**Multivariate**: Minimum Covariance Determinant (MCD)", 
-    "**Univariate**: robust *z* scores (MAD)"),
+    "**Model-based**: Cook (or Pareto for Bayesian models)",
+    "**Multivariate**: Minimum Covariance Determinant (MCD)",
+    "**Univariate**: robust *z* scores (MAD)"
+  ),
   `Recommended Threshold` = c(
-    "`qf(0.5, ncol(x), nrow(x) - ncol(x))` (or 0.7 for Pareto)", 
-    "`qchisq(p = 1 - 0.001, df = ncol(x))`", 
-    "`qnorm(p = 1 - 0.001 / 2)`, ~ 3.29")
+    "`qf(0.5, ncol(x), nrow(x) - ncol(x))` (or 0.7 for Pareto)",
+    "`qchisq(p = 1 - 0.001, df = ncol(x))`",
+    "`qnorm(p = 1 - 0.001 / 2)`, ~ 3.29"
+  )
 )
 knitr::kable(
-  df, col.names = gsub("[.]", " ", names(df)), 
-  caption = "Summary of Statistical Outlier Detection Methods Recommendations.", longtable = TRUE)
+  df,
+  col.names = gsub("[.]", " ", names(df)),
+  caption = "Summary of Statistical Outlier Detection Methods Recommendations.", longtable = TRUE
+)
 ```
 
 ## Cook's Distance vs. MCD
@@ -258,7 +263,7 @@ _Removing_ outliers can in this case be a valid strategy, and ideally one would
 The _easystats_ ecosystem makes it easy to incorporate this step into your workflow through the `winsorize()` function of *{datawizard}*, a lightweight R package to facilitate data wrangling and statistical transformations [@patil2022datawizard]. This procedure will bring back univariate outliers within the limits of 'acceptable' values, based either on the percentile, the _z_ score, or its robust alternative based on the MAD.
 
 ```{r winsorization}
-data[1501:1502, ]  # See outliers rows
+data[1501:1502, ] # See outliers rows
 # Winsorizing using the MAD
 library(datawizard)
 winsorized_data <- winsorize(data, method = "zscore", robust = TRUE, threshold = 3)