non-code critical fix for CRAN

DESCRIPTION

@@ -3,8 +3,8 @@ Type: Package
 Title: Tidy, Type-Safe 'prediction()' Methods
 Description: A one-function package containing 'prediction()', a type-safe alternative to 'predict()' that always returns a data frame. The 'summary()' method provides a data frame with average predictions, possibly over counterfactual versions of the data (a la the 'margins' command in Stata). Marginal effect estimation is provided by the related package, 'margins' <https://cran.r-project.org/package=margins>. The package currently supports common model types (e.g., "lm", "glm") from the 'stats' package, as well as numerous other model classes from other add-on packages. See the README or main package documentation page for a complete listing.
 License: MIT + file LICENSE
-Version: 0.3.11
-Date: 2018-11-25
+Version: 0.3.12
+Date: 2019-01-22
 Authors@R: c(person("Thomas J.", "Leeper",
                     role = c("aut", "cre"), 
                     email = "[email protected]",
@@ -45,7 +45,6 @@ Enhances:
     mclogit,
     mda,
     mlogit,
-    mnlogit,
     MNP,
     nlme,
     nnet,
@@ -61,4 +60,5 @@ Enhances:
     truncreg,
     VGAM
 ByteCompile: true
+Encoding: UTF-8
 RoxygenNote: 6.1.1

R/margex.R

@@ -28,13 +28,13 @@
 #' # . regress y i.sex i.group
 #' # . margins sex
 #' m1 <- lm(y ~ factor(sex) + factor(group), data = margex)
-#' prediction(m1, at = list(sex = 0:1))
+#' prediction(m1, at = list(sex = c("male", "female")))
 #' 
 #' # A simple case after logistic
 #' # . logistic outcome i.sex i.group
 #' # . margins sex
 #' m2 <- glm(outcome ~ sex + group, binomial(), data = margex)
-#' prediction(m2, at = list(sex = 0:1))
+#' prediction(m2, at = list(sex = c("male", "female")))
 #' 
 #' # Average response versus response at average
 #' # . margins sex