The Fitting Optimization Path Analysis on Scale Missing Data: Based on the 507 Patients of Poststroke Depression Measured by SDS

Table 2

The item missing conditions of the simulation sets under MCAR (N = 507).

Number of missing items (n (%))	5%	10%	15%	20%	25%	30%	35%	40%
0	187 (36.9)^a	58 (11.4)	17 (3.4)	7 (1.4)	1 (0.2)	1 (0.2)	0 (0)	0 (0)
1	183 (73.0)	146 (40.2)^a	82; (19.6)	33 (7.9)	12 (2.6)	6 (1.4)	0 (0)	1 (0.2)
2	94 (91.5)^b	135 (66.8)	101 (39.5)^a	66 (20.9)	34 (9.3)	12 (3.7)	3 (0.6)	2 (0.6)
3	36 (98.6)	96 (85.7)^b	134 (65.9)	114 (43.4)^a	79 (24.9)	38 (11.2)	18 (4.1)	7 (2.0)
4	7 (100.0)	49 (95.4)	85 (81.7)^b	102 (63.5)	80 (40.6)^a	59 (22.9)	36 (11.2)	21 (6.1)
5	0 (0)	17 (98.8)	53 (92.2)	92 (81.7)^b	104 (61.1)	107 (44.0)^a	60 (23.1)	41 (14.2)
6	0 (0)	5 (99.8)	21 (96.3)	54 (92.3)	88 (78.5)^b	79 (59.6)	93 (41.4)^a	57 (25.4)^a
7	0 (0)	1 (100.0)	9 (98.1)	22 (96.6)	56 (89.5)	92 (77.7)^b	91 (59.4)	74 (40.0)
8	0 (0)	0 (0)	4 (98.9)	12 (99.0)	29 (95.3)	46 (86.8)	93 (77.7)^b	83 (56.4)
9	0 (0)	0 (0)	1 (100.0)	4 (99.8)	16 (98.4)	43 (95.3)	56 (88.8)	96 (75.3)^b
10	0 (0)	0 (0)	0 (0)	0 (0)	6 (99.6)	13 (97.8)	35 (95.7)	60 (87.1)
11	0 (0)	0 (0)	0 (0)	1 (100.0)	2 (100.0)	9 (99.6)	13 (98.2)	42 (95.4)
12	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)	1 (99.8)	8 (99.8)	12 (97.8)
13	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)	1 (100.0)	1 (100.0)	7 (99.2)
14	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)	0 (0)	4 (100.0)

^aThe number of missing samples accounts for 25% of the total. ^bThe number of missing samples accounts for 75% of the total.