Macartan Humphreys

add parameter names to sort_by_list

2

parameter names were getting lost with `reshape_diagnosis` when select invoked see below note also that the final test in test-reshape-diagnosis is not reliable as it may produce a vector of...

trouble using lapply with design list

1

``` designs

default values for handlers not picked up in declarations?

4

``` f

designs as strategies

9

JC and I were chatting about designs in which the steps you take depend upon results from previous steps. For example gather more data, or nor, conditional on results of...

error with variable length hierarchical data

6

this warning seems to appear when the second level N is determined by the first level *and* there is a potential oucoems cll ``` > fabricate( + A = add_level(N...

IV designer -- add overidentification tests

2

add overidentification tests and multiple instruments add estimand from eq 4.4 of Imbens "Instrumental Variables: An Econometrician’s Perspective" : a linear (not necessarily convex) combination of effects for compliers and...

Factorial

1

1. Remove weights from estimation 2. Allow people to provide potential outcomes as formula Y = 1+ 2*T1 etc which can be transformed into outcome_means using sthg like If(is.null(outcome means))...

ICC

1

Think it worthwhile making ICC an explicit argument of the cluster designers. Currently it is set when all other vars are set. Think this requires something like, in arguments: ```...

binary outcomes

4

Suggest the canonical designers should have binary outcome option using probit type dgp Documentation change to reflect outcome_means etc are defined on the latent space if binary invoked Alernative is...