diff --git a/R/rep_glm.R b/R/rep_glm.R
index 1cd5225..850a27d 100644
--- a/R/rep_glm.R
+++ b/R/rep_glm.R
@@ -9,7 +9,15 @@
 #' @keywords logistic regression
 #' @export
 #' @examples
-#' rep_glm()
+#' l<-5
+#' y<-factor(rep(c("a","b"),l))
+#' x<-rnorm(length(y), mean=50, sd=10)
+#' v1<-factor(rep(c("r","s"),length(y)/2))
+#' v2<-sample(1:100, length(y), replace=FALSE)
+#' v3<-as.numeric(1:length(y))
+#' d<-data.frame(y,x,v1,v2,v3)
+#' preds<-dput(names(d)[3:ncol(d)])
+#' rep_glm(meas="y",vars="x",string=preds,ci=FALSE,data=df)
 
 rep_glm<-function(meas,vars,string,ci=FALSE,data){
   ## x is data.frame of predictors, y is vector of an aoutcome as a factor
@@ -88,3 +96,4 @@ rep_glm<-function(meas,vars,string,ci=FALSE,data){
 
   return(r)
 }
+
diff --git a/man/rep_glm.Rd b/man/rep_glm.Rd
index aacf28d..e4832ed 100644
--- a/man/rep_glm.Rd
+++ b/man/rep_glm.Rd
@@ -21,7 +21,15 @@ rep_glm(meas, vars, string, ci = FALSE, data)
 For bivariate analyses. The confint() function is rather slow, causing the whole function to hang when including many predictors and calculating the ORs with CI.
 }
 \examples{
-rep_glm()
+l<-5
+y<-factor(rep(c("a","b"),l))
+x<-rnorm(length(y), mean=50, sd=10)
+v1<-factor(rep(c("r","s"),length(y)/2))
+v2<-sample(1:100, length(y), replace=FALSE)
+v3<-as.numeric(1:length(y))
+d<-data.frame(y,x,v1,v2,v3)
+preds<-dput(names(d)[3:ncol(d)])
+rep_glm(meas="y",vars="x",string=preds,ci=FALSE,data=df)
 }
 \keyword{logistic}
 \keyword{regression}