Expressing intervention effects
When expressing the results of segmented regression
modelling, we can either report level
and trend changes like those in Table 1a or 1b,
or we can compare estimated post-intervention
values of the outcome to values estimated at that
time but based on baseline level and trend only,
as if the intervention had not occurred (the
counterfactual value). We can express the intervention
effect as the absolute difference between
the predicted outcome based on the intervention
and the counterfactual value, or as the ratio of
the predicted to the counterfactual value (usually
expressed as a percentage increase or decrease).
To estimate the cap effect in New Hampshire,
let us express the expected results from
regression equation 1 at month 26, which is
six months after the three-drug cap was implemented
Expressing intervention effectsWhen expressing the results of segmented regressionmodelling, we can either report leveland trend changes like those in Table 1a or 1b,or we can compare estimated post-interventionvalues of the outcome to values estimated at thattime but based on baseline level and trend only,as if the intervention had not occurred (thecounterfactual value). We can express the interventioneffect as the absolute difference betweenthe predicted outcome based on the interventionand the counterfactual value, or as the ratio ofthe predicted to the counterfactual value (usuallyexpressed as a percentage increase or decrease).To estimate the cap effect in New Hampshire,let us express the expected results fromregression equation 1 at month 26, which issix months after the three-drug cap was implemented
การแปล กรุณารอสักครู่..
