. Author manuscript; available in PMC: 2023 Aug 1.

Published in final edited form as: Stat Med. 2016 Feb 16;35(16):2831–2844. doi: 10.1002/sim.6900

Table 3:

Empirical size and power (%) of testing $Δ_{S \to M Y} . Q_{1}$ : model with only main effects; $Q_{2}$ : model with main effects and microRNA-by-expression interaction; $Q_{3}$ : model with main effects and two-way interactions; $Q_{4}$ : model with main effects, two-way and three-way interactions; Omnibus: the omnibus test for $Q_{1} - Q_{4}$ ; Score test: the classic score test for $β ’ s$ . The tuning parameter $λ$ was chosen using GCV.

	Null		Alternative
$β_{S}$	0	0.4	0	0	0.3	0.3	0.3	0.1	0.1	0	0
$β_{M}$	0	0	0.3	0	0.1	0.2	0.3	0	0	0	0
$β_{G}$	0	0	0	0.3	0.2	0.2	0.2	0	0	0	0
$β_{M G}$	0	0	0	0	0	0	0	0.3	0.5	0	0
$β_{S M}$	0	0	0	0	0	0	0	0.3	0.5	0	0
$β_{S G}$	0	0	0	0	0	0	0	0.3	0.5	0	0
$β_{S M G}$	0	0	0	0	0	0	0	0	0	0.5	1.0
$Q_{1}$	4.65	5.00	89.8	83.0	62.9	87.8	98.2	4.90	5.15	47.2	78.3
$Q_{2}$	5.25	5.35	86.0	75.8	57.0	83.5	96.6	7.45	9.65	43.4	73.6
$Q_{3}$	5.55	4.80	76.9	65.4	44.9	72.8	92.9	49.1	93.3	36.3	67.3
$Q_{4}$	4.30	4.60	73.9	59.0	41.7	69.6	91.3	41.0	87.3	80.6	99.0
Omnibus	5.30	4.65	86.4	76.6	55.9	83.2	96.6	33.9	85.5	69.6	97.4
Score test	51.0	49.0