Skip to main content

Table 3 Varying features in our simulation study

From: Evaluating the performance of propensity score matching based approaches in individual patient data meta-analysis

Features

 

Treatment prevalence

According to study

 

50%

 

30%

SD of the Random intercept

0.7

for outcome generation

1.4

 

2.1

SD of the random slope

0.04

for outcome generation

0.08

 

0.12

Pooled odds ratio for the

1

treatment effect, when

1.5

generating the outcome

3

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us