Macartan Humphreys

Understand why this is happening but not sure this is the best handling of these cases. * for the first case just implementing the normal in this case would make...

And some N arguments and some SD arguments I think ? On Mon, 25 Feb 2019, 17:09 Clara Bicalho, wrote: > This would apply to: > > - binary_iv arguments...

SGTM would it be possible to simply allow and function f that transforms Xb; default is identifiy but people cuolld do logits, probits exponentials, create counts or whatever, at tehri...

Yes, for example: $R = 1 iff a_R + b_R*Z > u_R$ $Y =1 iff a_Y + b_Y*Z > u_Y$ $(u_R, u_Y) ~ N(0, \Sigma)$ maybe nicer to write as...

Thanks Tara. @jaspercooper I did some edits in branch iv_small_edits that adds in ITT and changes default; love to get your thoughts @all I think the ate should definitely be...

Luke -- has it be possible to check this implementation against others in R or stata? On Wed, Oct 24, 2018 at 3:37 PM Luke Sonnet wrote: > *@lukesonnet* commented...

Maybe consult with Peter or Cyrus There are options, eg pool up and include warning. This would be like a local homoskedacticity assumption I suppose but could imagine being preferable...

I see that I'd be happy with a tank default and force collapse option On Tue, 9 Oct 2018, 00:01 Graeme Blair, wrote: > I guess to me choking seems...

Not wt machine now but if I remember I got the warning alright but the behavior was bad. I had all big blocks and only one block with a pair....

Apologies if we have gone over before but in mixed cases is it not possible to use matched pair approach for all matched pairs and block approach for larger blocks...