Update to mice 3.19.10

Author: stefvanbuuren

.Rbuildignore

@@ -23,3 +23,4 @@ vignettes/
 ^CRAN-SUBMISSION$
 ^scratch$
 ^Rplots\.pdf$
+^.claude$

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: mice
 Type: Package
-Version: 3.19.9
+Version: 3.19.10
 Title: Multivariate Imputation by Chained Equations
-Date: 2026-06-01
+Date: 2026-06-05
 Authors@R: c(person("Stef", "van Buuren", role = c("aut","cre"),
     email = "stef.vanbuuren@tno.nl"),
     person("Karin", "Groothuis-Oudshoorn", role = "aut",

NEWS.md

@@ -1,9 +1,27 @@
+# mice 3.19.10
+
+- Fixes `barnard.rubin()` silently returning only the first element when called
+  with vector `b` and `dfcom = Inf`. The infinite-`dfcom` branch used a scalar
+  `if`, so only the length-1 result was returned instead of a vector matching
+  `b`. Now vectorised with `ifelse()`, consistent with the finite-`dfcom` case.
+- Cleans up the testthat suite: restores or removes commented-out tests,
+  replaces deprecated `context()`/`expect_is()` calls, guards optional-package
+  tests with `skip_if_not_installed()`, and fixes a handful of latent test bugs
+  (a `set.seed <- 818` typo that silently disabled seeding, and a tautological
+  assertion in `test-blocks.R`). No user-facing behavior changes.
+- Adds a stable `<FUNCTION>-<NNN>` ID (e.g. `BARNARD-RUBIN-001`) to every
+  `test_that()` label in the testthat suite, derived from the test file name
+  and assigned in file order. These IDs let this R suite be compared directly
+  against other implementations that share the same scheme,
+  so equivalent test cases are greppable across languages instead of relying
+  on manual cross-referencing. No user-facing behavior changes.
+
 # mice 3.19.9
+
 - Adds `mice.impute.svm()` as a binary variables imputation technique for high 
   dimensional data based on proper multiple imputation using Support Vector 
   Machines combined with bootstrapping. Solves (#751) with (#752). Thanks @Mmtakahashi123
 
-
 # mice 3.19.8
 
 - Implements new behavior in `mice.mids() that inherits the imputation methods from the trained imputation model rather than re-initializing methods anew. This gives consistent behavior between train and deployment imputation models ([#753](https://github.com/amices/mice/issues/753))

README.Rmd

@@ -23,7 +23,7 @@ set.seed(1)
 [![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/mice)](https://cran.r-project.org/package=mice)
 [![](https://cranlogs.r-pkg.org/badges/mice)](https://cran.r-project.org/package=mice)
 [![R-CMD-check](https://github.com/amices/mice/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/amices/mice/actions/workflows/R-CMD-check.yaml)
-[![](https://img.shields.io/badge/github%20version-3.19.9-orange.svg)](https://amices.org/mice/)
+[![](https://img.shields.io/badge/github%20version-3.19.10-orange.svg)](https://amices.org/mice/)
 <!-- badges: end -->
 
 ## [Multivariate Imputation by Chained Equations](https://amices.org/mice/)

README.md

@@ -7,7 +7,7 @@
 [![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/mice)](https://cran.r-project.org/package=mice)
 [![](https://cranlogs.r-pkg.org/badges/mice)](https://cran.r-project.org/package=mice)
 [![R-CMD-check](https://github.com/amices/mice/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/amices/mice/actions/workflows/R-CMD-check.yaml)
-[![](https://img.shields.io/badge/github%20version-3.19.9-orange.svg)](https://amices.org/mice/)
+[![](https://img.shields.io/badge/github%20version-3.19.10-orange.svg)](https://amices.org/mice/)
 <!-- badges: end -->
 
 ## [Multivariate Imputation by Chained Equations](https://amices.org/mice/)
@@ -96,9 +96,9 @@ fit <- with(imp, lm(chl ~ age + bmi))
 # pool and summarize the results
 summary(pool(fit))
 #>          term estimate std.error statistic    df p.value
-#> 1 (Intercept)     9.08     73.09     0.124  4.50  0.9065
-#> 2         age    35.23     17.46     2.017  1.36  0.2377
-#> 3         bmi     4.69      1.94     2.417 15.25  0.0286
+#> 1 (Intercept)    12.01     70.99     0.169  4.31  0.8733
+#> 2         age    31.04     18.73     1.657  1.20  0.3134
+#> 3         bmi     4.84      1.88     2.572 16.20  0.0203
 ```
 
 The complete-data is fit to each imputed dataset, and the results are