MatchIt Marginal Effects

Question

I am trying to estimate the ATT of a treatment with MatchIt and am unsure if it is a marginal effect or a conditional effect. In the vignette for estimating the outcome, it says:

In addition, with continuous outcomes, conditional effects can be mistakenly interpreted as marginal effect estimates when treatment-covariate interactions are present in the outcome model. If the covariates are not centered at their mean in the target population (e.g., the treated group for the ATT, the full sample for the ATE, or the remaining matched sample for an ATM), the coefficient on treatment will not correspond to the marginal effect in the target population; it will correspond to the effect of treatment when the covariate values are equal to zero, which may not be meaningful or plausible. G-computation is always the safest way to estimate effects when including covariates in the outcome model, especially in the presence of treatment-covariate interactions.

Here, the outcome is continuous and in the outcome model I have a binary treatment, the matching variables X (all continuous) and an interaction. Since I am using G-Computation (I think), does this estimate a marginal effect?

m <- matchit(D ~ X,
         data = data,
         method = "cem", 
         estimand = "ATT", 
         k2k = FALSE)

matchdata <- match.data(m)

fit <- lm(Y ~ D + X + D * X,
      data = matchdata, weights = weights)

avg_comparisons(fit, variables = "D",
            vcov = "HC3", 
            newdata = subset(matchdata, D == 1),
            wts = "weights") 

Answer 1

Yes, as per the first sentence in the section "G-computation":

To estimate marginal effects, we use a method known as g-computation

G-computation allows you to estimate marginal effects regardless of the outcome model form. That's the whole point of using it.