Skip to main content

Table 4 Monte-carlo mean of F-statistics in each scenario using the treatment prescribed to the last patient 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

8.13

13.99

45.30

 

Med

12.18

15.66

49.45

 

Low

13.50

16.18

50.83

20000

    
 

High

8.47

10.94

32.26

 

Med

11.98

12.11

32.99

 

Low

13.35

13.79

31.93

10000

    
 

High

8.25

8.07

18.48

 

Med

10.69

9.80

18.88

 

Low

14.17

10.38

19.76

  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