TABLE 7.
The p-values, η2p and CIs of the effect size, of the four TEACh conditions.
| Type of attention | Interaction | Simple main effect | ||||
| Group*Time p-value | η2p [95% CI] | Group p-value | η2p [95% CI] | Time p-value | η2p [95% CI] MD [95% CI] | |
| Sus-AA | 0.242 | 0.057 [0.000, 0.192] | – | – | – | – |
| Div-AVA | 0.014* | 0.162 [0.007, 0.325] | 0.001** (baseline) 0.953 (3 months) 0.888 (6 months) | 0.380 [0.086, 0.583] 0.000 [0.000, 0.006] 0.001 [0.000, 0.032] | 0.492 (Control) 0.009** (RMHA) 0.121 (0–3 months) 0.002** (0–6 months) 1.000 (3–6 months) | 0.057 [0.000, 0.239] 0.325 [0.027, 0.523] 2.769 [−0.578, 6.117] 3.385 [1.381, 5.338] 0.615 [−2.678, 3.909] |
| Sel-VA | 0.074† | 0.103 [0.000, 0.256] | – | – | – | – |
| Div-AA | 0.781 | 0.010 [0.000, 0.087] | – | – | – | – |
The assumption of homogeneity of variances was violated in the Sus-AA and Div-AVA conditions. For both subtests, data transformations were not able to meet the assumption of homogeneity of variances, while other assumptions would also become violated. Violation of this assumption of homogeneity of variances increases the probability of a Type I error, but when sample sizes are equal and normally distributed a Type I error is less likely to occur (Box, 1953; Nordstokke and Zumbo, 2007). For these reasons, analysis for both subtests was carried out without adjustments. CI, Confidence Interval; Div-AA, Divided Auditory Attention; Div-AVA, Divided Auditory-Visual Attention; MD, Mean Difference; RMHA, Remote Microphone Hearing Aid; Sel-VA, Selective Visual Attention; Sus-AA, Sustained Auditory Attention; TEACh, Test of Everyday Attention for Children. †p < 0.10, *p < 0.05, **p < 0.01.