Hi Nathan,

Great question! Thanks for this. There are a few ways of doing it, but I think the method below is easiest. There is some weird code in there due to a problem with `dplyr::mutate()`

stripping parameters from the `simulations`

data.frame (see here, we’re working on fixing). But basically, it leverages the fact that `diagnose_design()`

can also just take a data.frame and use that for diagnosis.

```
library(tidyverse)
multiple_comparisons <-
declare_population(
N = 100,
X1 = rnorm(N),
X2 = rnorm(N),
X3 = rnorm(N),
X4 = rnorm(N)
) +
declare_estimand(true_effect = 0) +
declare_estimator(X1 ~ X2, model = lm_robust, estimand = "true_effect", label = "X1 on X2") +
declare_estimator(X2 ~ X3, model = lm_robust, estimand = "true_effect", label = "X2 on X3") +
declare_estimator(X3 ~ X4, model = lm_robust, estimand = "true_effect", label = "X3 on X4") +
declare_estimator(X1 ~ X4, model = lm_robust, estimand = "true_effect", label = "X1 on X4")
simulations <-
simulate_design(multiple_comparisons, sims = 20) %>%
group_by(sim_ID) %>%
mutate(p.value = p.adjust(p.value, method = "holm")) %>%
as.data.frame()
attr(simulations,"parameters") <- data.frame(design_label = "multiple_comparisons")
diagnose_design(simulations)
```