Merge 6538a29 into 23a0299

.travis.yml

@@ -34,13 +34,15 @@ matrix:
     - os: osx
       r: release
       if: branch = master
+      fortran: false 
       r_github_packages:
       - DeclareDesign/DDtools
       - DeclareDesign/DeclareDesign
       - ropensci/git2r
 
     - os: osx
       r: 3.4
+      fortran: false 
       r_github_packages:
       - DeclareDesign/DDtools
       - DeclareDesign/DeclareDesign

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: DesignLibrary
 Type: Package
 Title: Library of Research Designs
-Version: 0.1.1.9000
+Version: 0.1.2
 Authors@R: c(person("Graeme", "Blair", email = "graeme.blair@ucla.edu", role = c("aut")),
              person("Jasper", "Cooper", email = "jjc2247@columbia.edu", role = c("aut", "cre")),
              person("Alexander", "Coppock", email = "alex.coppock@yale.edu", role = c("aut")),

NEWS.md

@@ -1,3 +1,31 @@
+# DesignLibrary 0.1.2
+
+* Renamed and deprecated `simple_*` designers: 
+  - `simple_two_arm_designer() -> two_arm_designer()`, 
+  - `simple_spillover_designer() -> spillover_designer()`, 
+  - `simple_iv_designer() -> binary_iv_designer()`, 
+  - `simple_factorial_designer() -> two_by_two_designer()`  
+
+* Added tests for new `DeclareDesign` functionality
+
+* Updated names of `DeclareDesign` helpers (`draw_estimates`, etc.)
+
+* Enabled specification of block-level assignment probabilities in `block_cluster_two_arm_designer()`
+
+* Fixed a bug in `factorial_designer()` and `multi_arm_designer()` that was breaking substitution when `fixed = ` argument was used
+
+* Small cosmetic edits to `pretest_posttest_designer()`
+
+* Fixed estimator labels in `multi_arm_designer()`
+
+* Small updates to warning and error messages in: 
+  - `block_cluster_two_arm_designer()`
+  - `cluster_sampling_designer()`
+
+* Added PR template for contributing designers 
+
+* Improved handling of variance in `block_cluster_two_arm_designer()`, including verbose messaging
+
 # DesignLibrary 0.1.1
 
 * Added designer for process-tracing designs (`process_tracing_designer()`)

R/spillover_designer.R

@@ -11,8 +11,6 @@
 #' 
 #' The default estimand is the average difference across subjects between no one treated and only that subject treated.  
 #' 
-#' See \href{https://declaredesign.org/library/articles/spillover.html}{vignette online}.
-#' 
 #' @param N_groups An integer. Number of groups.
 #' @param N_i_group Number of units in each group. Can be scalar or vector of length \code{N_groups}.
 #' @param sd_i A nonnegative number. Standard deviation of individual-level shock.

R/two_arm_designer.R

@@ -7,8 +7,6 @@
 #' @details 
 #' Units are assigned to treatment using complete random assignment. Potential outcomes are normally distributed according to the mean and sd arguments.
 #' 
-#' See \href{https://declaredesign.org/library/articles/two_arm.html}{vignette online}.
-#' 
 #' @param N An integer. Sample size.
 #' @param assignment_prob A number in [0,1]. Probability of assignment to treatment.
 #' @param control_mean A number. Average outcome in control.

cran-comments.md

@@ -2,11 +2,11 @@
 
 * local OS X install, R 3.5.1
 * local Windows install 8 x64 (build 9200), R 3.5.1
-* ubuntu 14.04.5 LTS (on travis-ci), R 3.5.0 (2017-01-27)
+* ubuntu 14.04.5 LTS (on travis-ci), R 3.5.1 (2017-01-27)
 * ubuntu 14.04.5 LTS (on travis-ci), R 3.4.4 (2017-01-27)
-* ubuntu 14.04.5 LTS (on travis-ci), R Under development (unstable) (2018-08-24 r75179)
 * macOS High Sierra 10.13.3 (on travis-ci), R 3.5.0 (2018-04-23)
 * macOS High Sierra 10.13.3 (on travis-ci), 3.4.4 (2018-03-15)
+* ubuntu 14.04.5 LTS (on travis-ci), R Under development (unstable) (2018-10-29 r75510)
 
 ## R CMD check results