SAMURAI: Sensitivity analysis of a meta-analysis with unpublished but registered analytical investigations (software)

Table 2 Default standardized mean differences (SMD) assigned to unpublished studies with continuous outcomes

Outlook	Depends on published studies?	If the outcome event is desired (higher.is.better = T)	If the outcome event is undesired (higher.is.better = F)
‘very positive’	No	0.8	−0.8
‘positive’		0.3	−0.3
‘no effect’		0	0
‘negative’		−0.3	0.3
‘very negative’		−0.8	0.8
‘very positive CL’	Yes, depends on CL of published studies	UCL, _pub,1-α	LCL, _pub,1-α
‘positive CL’		$0.5 ({\hat{SMD}}_{pub} + UC L_{pub, 1 - α})$	$0.5 ({\hat{SMD}}_{pub} + LC L_{pub, 1 - α})$
‘current effect’		${\hat{SMD}}_{pub}$	${\hat{SMD}}_{pub}$
‘negative CL’		$0.5 ({\hat{SMD}}_{pub} + LC L_{pub, 1 - α})$	$0.5 ({\hat{SMD}}_{pub} + UC L_{pub, 1 - α})$
‘very negative CL’		LCL, _pub,1-α	UCL, _pub,1-α

Note: ‘Positive’ outlooks favor the experimental treatment arm and ‘negative’ outlooks favor the control treatment arm.
SMD: Standardized mean difference.
LCL: Lower confidence limit.
UCL: Upper confidence limit. ${\hat{SMD}}_{pub}$ : The summary SMD across all published studies.
(LCL _pub,1-α, UCL _pub,1-a): The 1-α confidence interval of ${\hat{SMD}}_{pub}$ .

ISSN: 2046-4053