Skip to main content

Table 3 Monte-carlo mean of F-statistics in each scenario using the proportion of patients who received the same treatment as proxy of instrument

From: Instrumental variable analysis in the context of dichotomous outcome and exposure with a numerical experiment in pharmacoepidemiology

n

Level

Weak

Mod

Strong

30000

    
 

High

14.14

101.32

432.00

 

Med

16.95

105.93

458.32

 

Low

17.65

108.05

465.88

20000

    
 

High

11.47

69.15

290.29

 

Med

13.49

71.53

302.10

 

Low

15.93

75.59

315.68

10000

    
 

High

8.96

36.64

147.29

 

Med

11.76

39.26

152.53

 

Low

12.48

42.80

161.04

  1. Legend: Low, Med (Medium), High denote level of confounding whereas Weak, Mod (Moderate), Strong stand for instrument strength. The number n with values 10000, 20000 and 30000 stands for the sample size