A systematic review of randomisation method use in RCTs and association of trial design characteristics with method selection

Table 4 The characteristics of each variable used to randomise split by randomisation method (stratification or minimisation)

Variable Characteristics		Stratified (n = 436)	Minimised (n = 206)
Variable type^a	Binary	157 (36)	80 (39)
	Categorical (Ordinal)	20 (5)	22 (11)
	Categorical (Non-Ordinal)	175 (40)	49 (24)
	Continuous	84 (19)	55 (27)
Variables form in randomisation if continuous	Binary	61 (73)	38 (69)
	Categorical	20 (24)	11 (20)
	Unknown	3 (4)	6 (11)
Number of categories ^b	2	233 (53)	128 (62)
	3	54 (12)	24 (12)
	4	19 (5)	11 (5)
	5 +	115 (26)	33 (16)
	Unknown	15 (4)	10 (5)
	Median (IQR)	2 (2,6)	2 (2,3)
	Mean (SD)	13 (48)	10 (29)

Unless otherwise specified, the table reports the number of studies along with column percentages
^a Variable type refers to the form of the variable separate of how it was included in the randomisation. In the minimisation group, 4 variables were classed as “other” so not included
^b Some categorical variables were split as binary to include in the randomisation. This includes 15 covariates that were stratified on and 10 covariates that were minimised

ISSN: 1471-2288