Study 2.2: Semantic decision

This online book is a reprint of:

Bernabeu, P. (2022). Language and sensorimotor simulation in conceptual processing: Multilevel analysis and statistical power. Lancaster University. https://doi.org/10.17635/lancaster/thesis/1795

Materials: https://osf.io/vyb8k

Convergence

In the initial model, the optimiser used (the default one in ‘lmerTest’) was ‘nloptwrap’, and the convergence warning read: ‘boundary (singular) fit: see ?isSingular’.

Based on the reanalysis using seven optimisers, Figure 33 shows the fixed, main effects, and Figure 34 shows the fixed interactions.

Code


# Display plot, which was produced in advance due to memory overload. Code available at:
# semanticdecision/frequentist_analysis/model_diagnostics/semanticdecision_allFit_convergence.R

include_graphics(
  paste0(
    getwd(),  # Circumvent illegal characters in file path
    '/semanticdecision/frequentist_analysis/model_diagnostics/plots/main_effects_semanticdecision_allFit_convergence.pdf'
  ))

Figure 33: Fixed, main effects from the semantic decision study fitted by seven optimisers.

Code


# Display plot, which was produced in advance due to memory overload. Code available at:
# semanticdecision/frequentist_analysis/model_diagnostics/semanticdecision_allFit_convergence.R

include_graphics(
  paste0(
    getwd(),  # Circumvent illegal characters in file path
    '/semanticdecision/frequentist_analysis/model_diagnostics/plots/interactions_semanticdecision_allFit_convergence.pdf'
  ))

Figure 34: Fixed interaction effects from the semantic decision study fitted by seven optimisers.

Residual errors not normally distributed

Figure 35 shows the deviation from normality of the residuals.

Code


# Display plot, which was produced in advance due to memory overload. Code available at:
# semanticdecision/frequentist_analysis/model_diagnostics/semanticdecision_residuals.R

include_graphics(
  paste0(
    getwd(),  # Circumvent illegal characters in file path
    '/semanticdecision/frequentist_analysis/model_diagnostics/plots/semanticdecision_residuals.png'
  ))

$Residuals of the linear mixed-effects model from the semantic decision study. \linebreak KS = Kolmogorov-Smirnov test; TS = tail-sensitive confidence bands.$

Figure 35: Residuals of the linear mixed-effects model from the semantic decision study. KS = Kolmogorov-Smirnov test; TS = tail-sensitive confidence bands.

Pablo Bernabeu, 2022. Licence: CC BY 4.0.
Thesis: https://doi.org/10.17635/lancaster/thesis/1795.

Online book created using the R package bookdown.