A mouse-tracking study of the composite nature of the Stroop effect at the level of response execution

Abstract

By forcing selection into response execution processes, the present mouse-tracking study investigated whether the ongoing process of response selection in the colour-word Stroop task is influenced by conflict and facilitation at both the level of response and stimulus. Mouse-tracking measures including partial errors provided credible evidence that both response and semantic conflict (i.e., distinct constituents of interference) contribute to the overall Stroop interference effect even after a response has been initiated. This contribution was also observed for the overall facilitation effect (that was credibly decomposed into response and semantic components in response times but not in mouse deviation measures). These results run counter to the dominant single-stage response competition models that currently fail to explain: 1) the expression of Stroop effects in measures of response execution and; 2) the composite nature of both interference and facilitation. By showing that Stroop effects-originating from multiple levels of processing-can cascade into movement parameters, the present study revealed the potential overlap between selection and execution process. It therefore calls for further theoretical efforts to account for when, where and under what conditions Stroop effects originating from different loci are controlled.

Fig 1. Trial types employed and comparisons made in the experiment to enable the indexing of the different components of the overall (congruency) Stroop effect.

Ink colours are paired: Green with red, blue with yellow. For colour-neutral and non-response set conditions, the words can be written with each colours of their pair (e.g., “Brown” written either in yellow or blue). Stroop components are calculated by subtracting the lower condition from the upper condition.

Fig 2. Spatial layout of the experimental display and illustration of the mouse deviation and x-coordinates.

The example displays a standard incongruent item (“rouge” [red] displayed in green). The grey curve represents a possible mouse trajectory response; the oblique dotted white line represents the direct path from the start point to the response. d_max denotes the (orthogonal) maximal deviation from the trajectory to the direct path with its corresponding orthogonal projection line on the direct path (long-dashed white line). Let t denote time sample numbers; d_t represent the trajectory’s (orthogonal) deviation at three time samples with their respective projection line (long-dashed blue lines); x_t indicates the x-coordinate of the trajectory at those three time samples, with their respective projection lines on the x-axis (short-dashed blue lines). Due to the trajectories’ alignment, the x-coordinate at the starting point of the trajectory is 0 (origin) and x-coordinate at end point (response) is 1 (displayed in the Figure). Negative x-coordinates are on the incorrect response side.

Fig 3. Distribution of mouse trajectories (observed for all conditions of the Stimulus-type factor) across the clusters (Cl) estimated through hierarchical cluster analysis.

The green lines represent each cluster’s average trajectory. Cl3, Cl4 and Cl8 are considered as partial error clusters for the purpose of estimating partial error rates.

Fig 4. Averaged time-normalized mouse trajectories aggregated by Stimulus-type.

Panel A: Stimulus-type conditions used for estimating interference components. Panel B: Stimulus-type conditions used for estimating facilitation components. To ensure comparability across trajectories, they were remapped rightward and their start/end points were aligned before time-normalization and aggregation by Stimulus-type and participant. Abbreviations: std.: standard, inc.: incongruent, cong: congruent.

Fig 5. Total Stroop effect (standard colour-incongruent–standard colour-congruent means) with Stroop interference (standard colour-incongruent–colour-neutral means) and facilitation (colour-neutral–standard colour-congruent means) components as a function of response times (Panel 5A), maximal mouse deviation (Panel 5B) and partial error rates (Panel 5C).

The magnitude and 99% CI of each component were estimated by contrasting the marginal means (i.e., marginal effects) of two types of stimuli computed from a fitted linear mixed model.

Fig 6. Total Stroop effect with interference (Panels A-C) and facilitation (Panels B-D) components as a function of normalized time.

These are estimated from the mouse deviation towards the incorrect side (A, B) and the X mouse coordinate (C, D). The Total Stroop effect is displayed in all plots for visual comparison purposes. Negative X-coordinates indicate a deviation towards the incorrect response (the plot’s y-axis is inverted for consistency with the other plot). The magnitude and 95% CI (shaded areas) of each component were estimated by contrasting the marginal means of two types of stimuli computed from a fitted linear mixed model (one LMM /time step and /measure, see the main text or Fig 5 caption for details of the contrasts). The straight lines at the top indicate the time steps where zero is not included in the 95% CI for at least 5 time-steps (in the main text, only intervals of at least 10 time-steps are reported).

Fig 7. Stroop interference (standard colour-incongruent–colour-neutral means) with response conflict (standard colour-incongruent–non-response set means), semantic conflict (colour-associated incongruent–colour-neutral means) and semantic relevance (non-response set–colour-associated incongruent means) components as a function of response times (Panel A), maximal mouse deviation (Panel B) and partial error rates (Panel C).

The magnitude and 99% CI of each component were estimated by contrasting the marginal means (i.e., marginal effects) of two types of stimuli computed from a fitted linear mixed model.

Fig 8. Stroop interference with response conflict (Panel A), semantic conflict (Panel B) and semantic relevance (Panel C) components estimated from the mouse deviation towards the incorrect side as a function of normalized time.

Stroop interference is displayed in all plots for visual comparison purposes. The magnitude and 95% CI (shaded areas) of each component were estimated by contrasting the marginal means of two types of stimuli computed from a fitted linear mixed model (one LMM /time step and /measure, see main text or Fig 7 caption for a detail of the contrasts). Top straight lines indicate the time steps where zero is not included in the 95% CI for at least 5 time-steps (in the main text, only intervals of at least 10-time steps are reported).

Fig 9. Stroop interference with (Panel A), semantic conflict (Panel B) and semantic relevance (Panel C) estimated from the X mouse coordinate as a function of normalized time.

Negative X-coordinates indicate a deviation towards the incorrect response (plot’s y-axis is inverted for consistency with the other plot). See Fig 8 caption for additional details.

Fig 10. Stroop facilitation (colour-neutral–standard colour-congruent means) with response (colour-associated congruent–standard colour-congruent means) and semantic (colour-neutral–colour-associated congruent means) facilitation components as a function of response times (Panel A), maximal mouse deviation (Panel B) and partial error rates (Panel C).

The magnitude and 99% CI of each component were estimated by contrasting the marginal means (i.e., marginal effects) of two types of stimuli computed from a fitted linear mixed model.

Fig 11. Stroop facilitation with response (Panels A-C) and semantic facilitation (Panels B-D) components as a function of normalized time.

These are estimated from the mouse deviation towards the incorrect side (A-B) and the X mouse coordinate (C-D). Stroop facilitation is displayed in all plots for visual comparison purposes. Negative X-coordinates indicate a deviation towards the incorrect response (plot’s y-axis is inverted for consistency with the other plot). The magnitude and 95% CI (shaded areas) of each component were estimated by contrasting the marginal means of two types of stimuli computed from a fitted linear mixed model (one LMM /time step and /measure, see main text or Fig 10 caption for a detail of the contrasts). Top straight lines indicate the time steps where zero is not included in the 95% CI for at least 5 time-steps (in the main text, only intervals of at least 10 time-steps are reported).