The R package simr has greatly facilitated power analysis for mixed-effects models using Monte Carlo simulation (i.e., hundreds or thousands of tests under slight variations of the data). The powerCurve function is used to estimate the statistical power for various sample sizes in one go. Since it runs serially, ...

Whereas the direction of main effects can be interpreted from the sign of the estimate, the interpretation of interaction effects often requires plots. This task is facilitated by the R package sjPlot (Lüdecke, 2022). For instance, using the plot_model function, I plotted the interaction between two continuous variables.

library(lme4)
#> Loading required package: Matrix
library(sjPlot)
library(ggplot2)

theme_set(theme_sjplot())

# Create data using code by Ben Bolker from 
# https://stackoverflow.com/a/38296264/7050882

set.seed(101)
spin = runif(600, 1, 24)
reg = runif(600, 1, 15)
ID = rep(c("1","2","3","4","5", "6", "7", "8", "9", "10"))
day = rep(1:30, each = 10)
testdata <- data.frame(spin, reg, ID, day)
testdata$fatigue <- testdata$spin * testdata$reg/10 * rnorm(30, mean=3, sd=2)

fit = lmer(fatigue ~ spin * reg + (1|ID),
           data = testdata, REML = TRUE)

plot_model(fit, type = 'pred', terms = c('spin', 'reg'))
#> Warning: Ignoring unknown parameters: linewidth

...

Whereas the direction of main effects can be interpreted from the sign of the estimate, the interpretation of interaction effects often requires plots. This task is facilitated by the R package sjPlot (Lüdecke, 2022). For instance, using the plot_model function, I plotted the interaction between two continuous variables.

library(lme4)
#> Loading required package: Matrix
library(sjPlot)
#> Learn more about sjPlot with 'browseVignettes("sjPlot")'.
library(ggplot2)

theme_set(theme_sjplot())

# Create data partially based on code by Ben Bolker  
# from https://stackoverflow.com/a/38296264/7050882

set.seed(101)

spin = runif(800, 1, 24)

trait = rep(1:40, each = 20)

ID = rep(1:80, each = 10)

testdata <- data.frame(spin, trait, ID)

testdata$fatigue <- 
  testdata$spin * testdata$trait / 
  rnorm(800, mean = 6, sd = 2)

# Model
fit = lmer(fatigue ~ spin * trait + (1|ID),
           data = testdata, REML = TRUE)
#> boundary (singular) fit: see help('isSingular')

plot_model(fit, type = 'pred', terms = c('spin', 'trait'))
#> Warning: Ignoring unknown parameters: linewidth

...

Whereas the direction of main effects can be interpreted from the sign of the estimate, the interpretation of interaction effects often requires plots. This task is facilitated by the R package sjPlot (Lüdecke, 2022). For instance, using the plot_model function, I plotted the interaction between a continuous variable and ...

To assess whether convergence warnings render the results invalid, or on the contrary, the results can be deemed valid in spite of the warnings, Bates et al. (2023) suggest refitting models affected by convergence warnings with a variety of optimizers. The authors argue that, if the different optimizers produce practically-equivalent results, ...

Linear mixed-effects models (LMM) offer a consistent way of performing regression and analysis of variance tests which allows accounting for non-independence in the data. Over the past decades, LMMs have subsumed most of the General Linear Model, with a steady increase in popularity (Meteyard & Davies, 2020). Since their conception, LMMs have ...

Whereas the direction of main effects can be interpreted from the sign of the estimate, the interpretation of interaction effects often requires plots. This task is facilitated by the R package sjPlot (Lüdecke, 2022). In Bernabeu (2022), the sjPlot ...

Frequentist and Bayesian statistics are sometimes regarded as fundamentally different philosophies. Indeed, can both methods qualify as philosophies, or is one of them just a pointless ritual? Is frequentist statistics about \(p\) values only? Are frequentist estimates diametrically opposed to Bayesian posterior distributions? Are confidence intervals and credible intervals irreconcilable? ...

Frequentist and Bayesian statistics are sometimes regarded as fundamentally different philosophies. Indeed, can both methods qualify as philosophies, or is one of them just a pointless ritual? Is frequentist statistics about \(p\) values only? Are frequentist estimates diametrically opposed to Bayesian posterior distributions? Are confidence intervals and credible intervals irreconcilable? ...

This post presents a code-through of a Bayesian workflow in R, which can be reproduced using the materials at https://osf.io/gt5uf. The content is closely based on Bernabeu (2022), which was in turn based on lots of other references. In addition to those, you may wish to consider ...

The function knit-deleting-service-files() is designed to avoid (R) Markdown knitting errors caused by service files from previous knittings (e.g., manuscript.tex, ZHJhZnQtYXBhLlJtZA==.Rmd, manuscript.synctex.gz). The function first suggests deleti...