easystats
I’m a bit puzzled about how to interpret check_outliers() and could use some guidance.
I’m a bit puzzled about how to interpret check_outliers() and could use some guidance.
I’m running some models and using check_outliers(), and I’m a bit unsure how to interpret the resulting plots.
For context: I simulated a dataset for my website to represent looking time in some participants. When I fit the model and run check_model(), the diagnostics don’t look too bad. However, the Influential observations plot from check_outliers() is a bit unclear to me.
Specifically:
-
No outliers are flagged by the function.
-
But many points appear outside the dotted reference lines, which I understood as a visual guide for potential outliers.
I hope this isn’t too basic a question — could you help me understand how to interpret this, or point me in the right direction?
library(lmerTest)
library(tidyverse)
library(easystats)
#> # Attaching packages: easystats 0.7.5
#> ✔ bayestestR 0.17.0 ✔ correlation 0.8.8
#> ✔ datawizard 1.2.0 ✔ effectsize 1.0.1
#> ✔ insight 1.4.2 ✔ modelbased 0.13.0
#> ✔ performance 0.15.1 ✔ parameters 0.28.1
#> ✔ report 0.6.1 ✔ see 0.11.0.7
df = read_csv("https://raw.githubusercontent.com/DevStart-Hub/DevStart/refs/heads/dev/resources/Stats/Dataset.csv")
df$Id = factor(df$Id)
df$Event = factor(df$Event)
df$SES = factor(df$SES)
df$TrialN = standardize(df$TrialN)
mod <- lmer(LookingTime ~ Event * TrialN + (1 + TrialN | Id), data = df)
check_model(mod)
check_outliers(mod)
#> OK: No outliers detected.
#> - Based on the following method and threshold: cook (0.7).
#> - For variable: (Whole model)
plot(check_outliers(mod))
Created on 2025-09-04 with reprex v2.1.1
Originally posted by @TommasoGhilardi in https://github.com/easystats/performance/discussions/856
