Impact of a mobile phone and web program on symptom and functional outcomes for people with mild-to-moderate depression, anxiety and stress: a randomised controlled trial

Table 4 Outcomes of mixed models analyses at baseline, post-intervention and follow-up for the myCompass and attention control groups

Effect	Contrast estimate	df (numerator, denominator)	F, tstatistic^a	p	Confidence intervals^b
*WSAS*
Group x time		2, 790	3.93	.020
Interaction contrasts:
Intervention phase^c	2.06	1, 790	2.77	.006	0.39-3.73
Follow-up phase	-0.93	1, 761	-1.07	.281	-2.81-1.01
*Depression*
Group x time		2, 803	7.94	.000
Interaction contrasts:
Intervention phase	3.22	1, 799	3.83	.000	1.33-5.10
Follow-up phase	-2.85	1, 774	-2.91	.004	-5.05--0.65
*DASS anxiety*
Group x time		2, 805	4.20	.015
Interaction contrasts:
Intervention phase	1.76	1, 802	2.76	.006	0.33-3.21
Follow-up phase	-1.62	1, 775	-2.18	.029	-3.29--0.05
*DASS stress*
Group x time		2, 800	5.33	.120
Interaction contrasts:
Intervention phase	1.48	1, 797	1.91	.056	-0.26-3.22
Follow-up phase	-0.30	1, 770	-0.33	.721	-2.33-1.72
*DASS total score*
Group x time		2, 801	6.15	.002
Interaction contrasts:
Intervention phase	6.73	1, 798	3.46	.001	2.91-10.55
Follow-up phase	-5.14	1, 771	-2.27	.024	-9.59--0.69

^aAs appropriate.
^bBonferroni adjusted confidence intervals, P = .025.
^cAlthough the model is different, the intervention phase contrasts answer the same question as those comparing the myCompass and Attention Control groups reported in Table 3.

ISSN: 1471-244X