bump version

Author: jgabry

.Rbuildignore

@@ -15,3 +15,4 @@ vignettes/loo2-lfo_cache/*
 vignettes/loo2-non-factorizable_cache/*
 ^\.appveyor\.yml$
 ^\.codecov\.yml$
+.github/*

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: loo
 Type: Package
 Title: Efficient Leave-One-Out Cross-Validation and WAIC for Bayesian Models
-Version: 2.2.0.9000
-Date: 2019-12-18
+Version: 2.3.0
+Date: 2020-07-06
 Authors@R: c(person("Aki", "Vehtari", email = "Aki.Vehtari@aalto.fi", role = c("aut")),
              person("Jonah", "Gabry", email = "jsg2201@columbia.edu", role = c("cre", "aut")),
              person("Mans", "Magnusson", role = c("aut")),

NEWS.md

@@ -1,13 +1,5 @@
-<!--
-# loo 2.3.0.9000
-
-(GitHub issue/PR number in parentheses)
-
-* Items for next release 
--->
 
-
-# loo 2.2.0.9000
+# loo 2.3.0
 
 (GitHub issue/PR number in parentheses)
 
@@ -21,6 +13,8 @@ update a `loo` object when Pareto k estimates are large. (#130)
 when returned to the user. This should be less confusing for anyone using 
 the `weights()` method to make an importance sampler. (#112, #146)
 
+* MCSE calculation is now deterministic (#116, #147)
+
 
 # loo 2.2.0