Kristoffer Bjärkefur

> New `treatment()` option should replace current `control()` option functionality Hesitant to remove `control()` due to backward compatibility, but if you elaborate on the benefit of a new option `treatment()`...

> There is no need for a separate `fixedeffect()` option as long as indicator `i.` variables can be appropriately included in the covariates() option I don't disagree if the command...

> `rowvarlabels` behavior should be the default, with the option to disable Again, I don't disagree if the command was new, but do not see what would justify to break...

> Table notes should explain the meaning of non-numerical results like `.v` Are you sure the table notes is the right place for this? Missing values should never end up...

> The default paired t-tests should also report their SEs by default, with the option of instead producing P-values and, possibly, confidence intervals. Risking to sound like a record on...

> `onerow` returns an unhelpful error if the number of observations varies across regressions. Agreed, I will implement

> > > There is no need for a separate `fixedeffect()` option as long as indicator `i.` variables can be appropriately included in the covariates() option > > > >...

> > > New `treatment()` option should replace current `control()` option functionality > > > > > > Hesitant to remove `control()` due to backward compatibility, but if you elaborate...

> > > I am not sure that the nrmd (normalized differences) are correctly calculated. See [this link](https://blogs.worldbank.org/impactevaluations/should-we-require-balance-t-tests-baseline-observables-randomized-experiments): > > > > > > @bbdaniels, can you give me a...

> > > Table notes should explain the meaning of non-numerical results like `.v` > > > > > > Are you sure the table notes is the right place...