robust estimation

DESCRIPTION

@@ -1,19 +1,20 @@
 Package: radiant.model
 Type: Package
 Title: Model Menu for Radiant: Business Analytics using R and Shiny
-Version: 0.8.2
-Date: 2017-5-22
+Version: 0.8.3
+Date: 2017-7-2
 Authors@R: person("Vincent", "Nijs", , "[email protected]", c("aut", "cre"))
 Description: The Radiant Model menu includes interfaces for linear and logistic
-    regression, neural networks, model evaluation, collaborative filtering,
+    regression, naive bayes, classification and regression trees, 
+    neural networks, model evaluation, collaborative filtering, 
     decision analysis, and simulation. The application extends the functionality 
     in radiant.data.
 Depends:
     R (>= 3.3.0),
-    radiant.data (>= 0.8.1)
+    radiant.data (>= 0.8.6)
 Imports:
-    radiant.basics (>= 0.8.0),
-    shiny (>= 1.0.0),
+    radiant.basics (>= 0.8.3),
+    shiny (>= 1.0.3),
     nnet (>= 7.3.12),
     NeuralNetTools (>= 1.4.0),
     sandwich (>= 2.3.4),

NAMESPACE

@@ -163,7 +163,9 @@ importFrom(stats,model.matrix)
 importFrom(stats,na.omit)
 importFrom(stats,pnorm)
 importFrom(stats,predict)
+importFrom(stats,pt)
 importFrom(stats,qnorm)
+importFrom(stats,qt)
 importFrom(stats,quantile)
 importFrom(stats,rbinom)
 importFrom(stats,residuals)

NEWS.md

@@ -1,11 +1,13 @@
-# CHANGES IN radiant.model 0.8.2
+# CHANGES IN radiant.model 0.8.3
 
-* Moved coefficient formatting summary.regress and logist.regress to make result$coeff more easily accessible
+* Moved coefficient formatting from summary.regress and summary.logistic to make result$coeff more easily accessible
 * Added F-score to _Model > Evaluate classification > Confusion_
+* Added option to use robust standard errors in _Linear regression_ and _Logistic regression_. The `HC1` covariance matrix is used to produce results consistent with Stata
 
 ## BUG FIXES
 
 * Fixed RSME typo
+* Don't calculate VIFs when stepwise regression selects only one explanatory variable
 
 # CHANGES IN radiant.model 0.8.0