You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Sometimes we'd want to add interaction terms to a model. For example, if we believe our propensity model may change over time, we may want to add interactions between all existing covariates and index year. These interaction terms themselves would just be new covariates from the perspective of the model fitting.
For example, the interaction between 'T2DM in the last 365 days' and 'index year: 2022' would be the covariate 'T2DM in the last 365 days AND index year: 2022', which would have the value 1 if T2DM was observed in the last 365 days and the index year is 2022.
The text was updated successfully, but these errors were encountered:
Sometimes we'd want to add interaction terms to a model. For example, if we believe our propensity model may change over time, we may want to add interactions between all existing covariates and index year. These interaction terms themselves would just be new covariates from the perspective of the model fitting.
For example, the interaction between 'T2DM in the last 365 days' and 'index year: 2022' would be the covariate 'T2DM in the last 365 days AND index year: 2022', which would have the value 1 if T2DM was observed in the last 365 days and the index year is 2022.
The text was updated successfully, but these errors were encountered: