Table 1. Repeated Measures ANOVA for Gaze Bias Score (N = 138).
Last Updated: 2019-04-07 13:44:37 code csv
index term SS MS N DF f Pr(>|f|)
1 cesd_group 0.001024 0.001024 1 136.000003 0.028533 0.8661
2 trialType 0.062013 0.062013 1 136.999995 1.727506 0.1909
index sigma logLik AIC BIC REMLcrit df.residual
1 0.189467 26.229889 -42.459778 -24.357774 -52.459778 271

Type III Analysis of Variance Table with Satterthwaite's method ['anova'].

Statistical Analysis

Participants with 'Dotloc' or 'Stimulus' Onset Error median above 3SD (n = 31, 18.7%) were excluded from analysis (see methods). We employed a repeated measures ANOVA using the anova() function in the stats R package (R Core Team, 2013; Chambers, Hastie, 1992). For our model, CESD Score ('Low' (<16) and 'High' (≥16)), and Stimulus (IAPS, POFA). were included as main effects. Random effects for Participant. was included in the model to account for their respective variation in their slopes and intercepts. Gaze Bias Score was used as the outcome measure.

For our analysis of Gaze Bias Score, our results revealed no statistically significant effect of CESD Score (F (1, 136) = 0.0285, p = 0.8661), no statistically significant effect of Stimulus (F (1, 136) = 1.7275, p = 0.1909).

Table 2. Pairwise Comparisons of Estimated Marginal Means.
Last Updated: 2019-04-07 13:44:37
index Contrasts estimate SE t Pr(>|t|)
1 High,0 - Low,0 0.005152 0.030499 0.168919 0.8661
2 High,0 - High,1 0.029979 0.022809 1.314346 0.4024
3 High,0 - Low,1 0.035131 0.038085 0.922438 0.5906
4 Low,0 - High,1 0.024827 0.038085 0.651890 0.6755
5 Low,0 - Low,1 0.029979 0.022809 1.314346 0.4024
6 High,1 - Low,1 0.005152 0.030499 0.168919 0.8661
The 'Estimated Marginal Means' table provides a list pairwise comparisons for each level and factor in our model (emmeans package, Version 1.3.2).
Figure 1. Pairwise Comparisons Plot.
Last Updated: 2019-04-07 13:44:37
This boxplot provides a comparison of [cesd_group] and across both IAPS and POFA stimuli. Both IAPS and POFA plots were nornalized to allow direct comparison.
Figure 2. Q-Q Plot (iaps, pofa).
Last Updated: 2019-04-07 13:44:37
The Normal Q-Q plot compares the standardized residuals against the theoretical quantiles from a standard normal distribution. If the model residuals are normally distributed, then the points on this graph will be plotted in a generally straight line.
Figure 3. Residuals vs Fitted Plot (iaps, pofa).
Last Updated: 2019-04-07 13:44:37
The Residuals vs Fitted plot is used to identify residual distribution. If residuals are following a visible trend on the graph, then the homogeneity assumption was violated.