Skip to main content

Table 6 Estimated probability of having one’s own observed treatment history and censoring history at follow-up

From: Marginal structural models for the estimation of the risk of Diabetes Mellitus in the presence of elevated depressive symptoms and antidepressant medication use in the Women’s Health Initiative observational and clinical trial cohorts

 

N

Mean

SD

Median

Quartile range

Minimum

Maximum

WHI-OS

36 months

       

Probability of having observed antidepressant medication history

  Given baseline covariates

64048

0.91

0.05

0.91

0.06

0.49

0.99

  Given time-varying covariates

64048

0.91

0.06

0.92

0.06

0.36

0.99

Probability of being uncensored

  Given baseline covariates

64099

0.99983

0.0000271

0.9998275

0.0000380

0.99963

0.99988

  Given time-varying covariates

64099

0.99983

0.0000273

0.9998275

0.0000381

0.99964

0.99988

WHI-CT

12 months

       

Probability of having observed antidepressant medication history

    

  Given baseline covariates

46084

0.93

0.05

0.94

0.05

0.52

0.995

  Given time-varying covariates

46084

0.93

0.05

0.94

0.05

0.30

0.996

Probability of being uncensored

  Given baseline covariates

46084

0.9999997

6.7564221E-8

0.9999997

9.1169629E-8

0.9999992

0.9999998

  Given time-varying covariates

46084

0.9999997

6.7917506E-8

0.9999997

9.1473164E-8

0.9999992

0.9999998

36 months

       

Probability of having observed antidepressant medication history

    

  Given baseline covariates

45235

0.86

0.09

0.88

0.10

0.24

0.99

  Given time-varying covariates

45235

0.86

0.09

0.88

0.10

0.20

0.99

Probability of being uncensored

  Given baseline covariates

45235

0.999971

6.6963806E-6

0.999971

9.041897E-6

0.99992

0.99998

  Given time-varying covariates

45235

0.999971

6.7459345E-6

0.999971

9.0819261E-6

0.99992

0.99998