Add ARD function to return ANCOVA results

[edelarua]

Create function to calculate statistics returned by tern::s_ancova().

Function summarizes results of emmeans::emmeans(stats::lm(formula)) and emmeans::contrast(fit, method = "trt.vs.ctrl") and should return the following statistics:

• n: Count of complete sample size for the group.
• lsmean: Estimated marginal means in the group.
• lsmean_diff: Difference in estimated marginal means in comparison to the reference group.
• lsmean_diff_ci: Confidence level for difference in estimated marginal means in comparison to the reference group.
• pval: p-value (not adjusted for multiple comparisons).

See https://insightsengineering.github.io/tern/latest-tag/reference/summarize_ancova.html for details on the tern function.

[ddsjoberg]

FYI, there is a function that returns lsmean_diff_ci in cardx (https://insightsengineering.github.io/cardx/main/reference/ard_emmeans_mean_difference.html). This function handles both continuous and binary endpoints. I don't know if it needs special handling for interaction terms?

I wonder if it's worth combining these functions or keeping two separate for LS mean and LS mean differences? Also, what should the name of the fn be? I think ANCOVA is too general, and I think I prefer something referencing LS means (also with our naming convention, it'll begin with ard_emmeans_*()