OHDSI Home | Forums | Wiki | Github

"Max number of people to include in the Propensity Score model"?

Hello.

In the Propensity Score adjustment window in Atlas there is an option…

“What is the maximum number of people to include in the Propensity Score model when fitting?”

As I understand that number is used to calculate the PS…
But can that PS then be used with the whole cohort in the final outcome model?
Or it should only be applied to the same sample of people?

The propensity model is computed on a sample of subjects for efficiency. It is then used to compute the propensity score for the full population

1 Like
t