u

R/rep_lm.R

@@ -1,89 +1,87 @@
 #' A repeated linear regression function
 #'
-#' For bivariate analyses.
+#' For bivariate analyses, to determine which variables to include in adjusted model.
-#' @param y Effect meassure.
+#' @param meas Effect meassure. Input as c() of columnnames, use dput().
-#' @param v1 Main variable in model
+#' @param vars variables in model. Input as c() of columnnames, use dput().
+#' @param string variables to test. Input as c() of columnnames, use dput().
+#' @param ci flag to get results as OR with 95% confidence interval.
+#' @param data data frame to pull variables from.
 #' @keywords linear regression
 #' @export
 #' @examples
 #' rep_lm()
 
-rep_lm<-function(y,v1,string,ci=FALSE,data,v2=NULL,v3=NULL){
+rep_lm<-function(meas,vars,string,ci=FALSE,data){
-## x is data.frame of predictors, y is vector of an aoutcome as a factor
-## output is returned as coefficient, or if ci=TRUE as coefficient with 95 % CI.
-## The confint() function is rather slow, causing the whole function to hang when including many predictors and calculating the ORs with CI.
 
   require(broom)
 
   d<-data
-  x<-select(d,one_of(c(string)))
+  x<-data.frame(d[,c(string)])
-  m1<-length(coef(lm(y~v1)))
+  v<-data.frame(d[,c(vars)])
+  y<-d[,c(meas)]
+  dt<-cbind(y,v)
+  m1<-length(coef(lm(y~.,data = dt)))
 
-if (is.factor(y)){stop("Some kind of error message would be nice, but y should not be a factor!")}
+  if (is.factor(y)){stop("Some kind of error message would be nice, but y should not be a factor!")}
 
-    if (ci==TRUE){
+  if (ci==TRUE){
 
-             df<-data.frame(matrix(ncol = 4))
+    df<-data.frame(matrix(ncol = 3))
-  names(df)<-c("pred","co_ci","pv","t")
+    names(df)<-c("pred","or_ci","pv")
 
-      for(i in 1:ncol(x)){
+    for(i in 1:ncol(x)){
-     m<-lm(y~v1+x[,i])
+      dat<-cbind(dt,x[,i])
+      m<-lm(y~.,data=dat)
 
-     l<-suppressMessages(round(confint(m)[-c(1:m1),1],2))
+      l<-suppressMessages(round(confint(m)[-c(1:m1),1],2))
-     u<-suppressMessages(round(confint(m)[-c(1:m1),2],2))
+      u<-suppressMessages(round(confint(m)[-c(1:m1),2],2))
-     co<-round(coef(m)[-c(1:m1)],2)
+      or<-round(coef(m)[-c(1:m1)],2)
+      or_ci<-paste0(or," (",l," to ",u,")")
+      pv<-round(tidy(m)$p.value[-c(1:m1)],3)
+      x1<-x[,i]
 
-     co_ci<-paste0(co," (",l," to ",u,")")
+      if (is.factor(x1)){
+        pred<-paste(names(x)[i],levels(x1)[-1],sep = "_")}
 
-     pv<-round(tidy(m)$p.value[-c(1:m1)],3)
+      else {pred<-names(x)[i]}
-     pv<-ifelse(pv<0.001,"<0.001",pv)
 
-        t <- ifelse(pv<=0.1|pv=="<0.001","include","drop")
+      df<-rbind(df,cbind(pred,or_ci,pv))}}
-
-     pv <- ifelse(pv<=0.05|pv=="<0.001",paste0("*",pv),
-                  ifelse(pv>0.05&pv<=0.1,paste0(".",pv),pv))
-
-
-    v<-x[,i]
-
-    if (is.factor(v)){
-       pred<-paste(names(x)[i],levels(v)[-1],sep = "_")
-    }
-
-       else {pred<-names(x)[i]}
-
-      df<-rbind(df,cbind(pred,co_ci,pv,t))
-
-    }}
 
   if (ci==FALSE){
 
-       df<-data.frame(matrix(ncol = 4))
+    df<-data.frame(matrix(ncol = 3))
-  names(df)<-c("pred","b","pv","t")
+    names(df)<-c("pred","b","pv")
 
-  for(i in 1:ncol(x)){
+    for(i in 1:ncol(x)){
-     m<-lm(y~v1+x[,i])
+      dat<-cbind(dt,x[,i])
 
-     b<-round(coef(m)[-c(1:m1)],3)
+      m<-lm(y~.,data=dat)
 
-     pv<-round(tidy(m)$p.value[-c(1:m1)],3)
+      b<-round(coef(m)[-c(1:m1)],3)
-     pv<-ifelse(pv<0.001,"<0.001",pv)
 
-    t <- ifelse(pv<=0.1|pv=="<0.001","include","drop")
+      pv<-round(tidy(m)$p.value[-c(1:m1)],3)
 
-     pv <- ifelse(pv<=0.05|pv=="<0.001",paste0("*",pv),
+      x1<-x[,i]
-                  ifelse(pv>0.05&pv<=0.1,paste0(".",pv),pv))
 
-     v<-x[,i]
+      if (is.factor(x1)){
+        pred<-paste(names(x)[i],levels(x1)[-1],sep = "_")
+      }
 
-     if (is.factor(v)){
+      else {pred<-names(x)[i]}
-       pred<-paste(names(x)[i],levels(v)[-1],sep = "_")
-     }
 
-       else {pred<-names(x)[i]}
+      df<-rbind(df,cbind(pred,b,pv))
 
-     df<-rbind(df,cbind(pred,b,pv,t))
+    }}
-  }}
+
-  result<-df
+  pa<-as.numeric(df[,3])
-  return(df)
+  pa<-ifelse(pa<0.001,"<0.001",pa)
+
+  t <- ifelse(pa<=0.1|pa=="<0.001","include","drop")
+
+  pa <- ifelse(pa<=0.05|pa=="<0.001",paste0("*",pa),
+               ifelse(pa>0.05&pa<=0.1,paste0(".",pa),pa))
+
+  r<-data.frame(df[,1:2],pa,t)[-1,]
+
+  return(r)
 }

man/rep_lm.Rd

@@ -4,15 +4,21 @@
 \alias{rep_lm}
 \title{A repeated linear regression function}
 \usage{
-rep_lm(y, v1, string, ci = FALSE, data, v2 = NULL, v3 = NULL)
+rep_lm(meas, vars, string, ci = FALSE, data)
 }
 \arguments{
-\item{y}{Effect meassure.}
+\item{meas}{Effect meassure. Input as c() of columnnames, use dput().}
 
-\item{v1}{Main variable in model}
+\item{vars}{variables in model. Input as c() of columnnames, use dput().}
+
+\item{string}{variables to test. Input as c() of columnnames, use dput().}
+
+\item{ci}{flag to get results as OR with 95% confidence interval.}
+
+\item{data}{data frame to pull variables from.}
 }
 \description{
-For bivariate analyses.
+For bivariate analyses, to determine which variables to include in adjusted model.
 }
 \examples{
 rep_lm()