Updated vignette

R/polyplot2.R

@@ -51,19 +51,19 @@ polyplot2 <- function(x,histogram=FALSE,curve=FALSE,main="PolyPlot2",xlab=NULL,x
   if (values) {
   labels0 <- round(c(mi,(mi+ma)/2,ma),digits); rR2 <- round((ma-mi)/2,digits);
   text(labels0,0,labels0,cex=.8,pos=3,col=col,font=2,offset=1);
-  mtext('R/2',side=4,at=0,cex=0.8,las=1,col=col,font=2); mtext(rR2,side=4,at=0,cex=0.8,las=1,col=col,font=2,padj=-1.6);
+  mtext('R/2',side=4,at=0,cex=0.8,las=1,col=col,font=2); mtext(rR2,side=4,at=0,cex=0.8,las=1,col=col,font=2,padj=-1.65);
   labels1 <- round(c(xmean-s,xmean,xmean+s),digits); rs <- round(s,digits); 
   text(labels1,y1,labels1,cex=.8,pos=3,col=col,font=2,offset=1);
-  mtext('SD',side=4,at=y1,cex=0.8,las=1,col=col,font=2); mtext(rs,side=4,at=y1,cex=0.8,las=1,col=col,font=2,padj=-1.6);
+  mtext('SD',side=4,at=y1,cex=0.8,las=1,col=col,font=2); mtext(rs,side=4,at=y1,cex=0.8,las=1,col=col,font=2,padj=-1.65);
   labels2 <- round(c(m1,xmean,m2),digits); rdelta <- round(delta,digits);
   text(labels2,y2,labels2,cex=.8,pos=3,col=col,font=2,offset=1);
-  mtext('MAD',side=4,at=y2,cex=0.8,las=1,col=col,font=2); mtext(rdelta,side=4,at=y2,cex=0.8,las=1,col=col,font=2,padj=-1.6);
+  mtext('MAD',side=4,at=y2,cex=0.8,las=1,col=col,font=2); mtext(rdelta,side=4,at=y2,cex=0.8,las=1,col=col,font=2,padj=-1.65);
   labels3 <- round(c(q1,xmed,q3),digits); riqr2 <- round(iqr/2,digits);
   text(labels3,y3,labels3,cex=.8,pos=3,col=col,font=2,offset=1)
-  mtext('IQR/2',side=4,at=y3,cex=0.8,las=1,col=col,font=2); mtext(riqr2,side=4,at=y3,cex=0.8,las=1,col=col,font=2,padj=-1.6);
+  mtext('IQR/2',side=4,at=y3,cex=0.8,las=1,col=col,font=2); mtext(riqr2,side=4,at=y3,cex=0.8,las=1,col=col,font=2,padj=-1.65);
   labels4 <- round(mode,digits);
   text(labels4,y4,labels4,cex=.8,pos=3,col=col,font=2,offset=1);
-  mtext('N',side=4,at=y4,cex=0.8,las=1,col=col,font=2); mtext(n,side=4,at=y4,cex=0.8,las=1,col=col,font=2,padj=-1.6);
+  mtext('N',side=4,at=y4,cex=0.8,las=1,col=col,font=2); mtext(n,side=4,at=y4,cex=0.8,las=1,col=col,font=2,padj=-1.65);
 }}
 
 tcol <- function(color,percent=30,name=NULL) {

docs/README.md

@@ -9,7 +9,7 @@ Scores <- c(rnorm(n=600,mean=100,sd=15),rnorm(n=200,mean=115,sd=20),rnorm(n=200,
 polyplot2(Scores)
 ```
 
-![](polyplot2.jpeg)<!-- -->
+![](./figures/polyplot2.jpeg)<!-- -->
 
 By default, the function labels all of the points and provides summary statistics in the margin. Generally speaking, each level/row provides a different category of measures of location and spread.
 
@@ -29,6 +29,6 @@ polyplot2(Scores,histogram=TRUE,curve=FALSE,values=FALSE,main="PolyPlot2 plus Hi
 polyplot2(Scores,histogram=FALSE,curve=TRUE,values=FALSE,main="PolyPlot2 plus Density Curve",col="darkblue",bg="darkgoldenrod")
 ```
 
-![](polyplot2plus.jpeg)<!-- -->
+![](./figures/polyplot2plus.jpeg)<!-- -->
 
 Further explanation of the polyplot and how it can be used to understand the shape of the distribution is available in Seier and Bonett (2011).

docs/scripts/polyplot2tutorial.R

@@ -0,0 +1,18 @@
+# polyplot2
+## Tutorial for PolyPlot2
+
+source("http://raw.githubusercontent.com/cwendorf/polyplot2/main/source-polyplot2.R")
+
+### The Basic PolyPlot
+
+#### In order to demonstrate the finer points of a PolyPlot, the following code simulates 1000 scores from a positively skewed unimodal distribution and then calls `polyplot2` using the default options.
+
+Scores <- c(rnorm(n=600,mean=100,sd=15),rnorm(n=200,mean=115,sd=20),rnorm(n=200,mean=130,sd=25))
+polyplot2(Scores)
+
+### Using the PolyPlot to Determine Shape
+
+#### The following code demonstrates some of the available options for customizing the PolyPlot.Similarly, it demonstrates how the PolyPlot does a good job of approximating the shape of the underlying distribution.
+par(mfrow=c(1,2))
+polyplot2(Scores,histogram=TRUE,curve=FALSE,values=FALSE,main="PolyPlot2 plus Histogram",col="darkblue",bg="darkgoldenrod")
+polyplot2(Scores,histogram=FALSE,curve=TRUE,values=FALSE,main="PolyPlot2 plus Density Curve",col="darkblue",bg="darkgoldenrod")

docs/vignettes/polyplot2tutorial.Rmd

@@ -0,0 +1,58 @@
+---
+title: "PolyPlot2"
+author: "Craig A. Wendorf"
+date: "`r Sys.Date()`"
+output:
+  html_document:
+    toc: true
+    toc_float: true
+    toc_depth: 4
+    collapse: true
+    theme: cerulean
+    highlight: tango
+    keep_md: TRUE
+vignette: >
+  %\VignetteIndexEntry{Tutorial for PolyPlot2}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+```{r,include=FALSE}
+#suppress the warnings and other messages from showing in the knitted file.
+knitr::opts_chunk$set(fig.width=7, fig.height=5,fig.path='figures/',echo=TRUE,warning=FALSE,message=FALSE)
+```
+
+```{r,include=FALSE}
+library(polyplot2)
+```
+
+## Tutorial for PolyPlot2
+
+### The Basic PolyPlot
+
+In order to demonstrate the finer points of a PolyPlot, the following code simulates 1000 scores from a positively skewed unimodal distribution and then calls `polyplot2` using the default options.
+
+```{r}
+Scores <- c(rnorm(n=600,mean=100,sd=15),rnorm(n=200,mean=115,sd=20),rnorm(n=200,mean=130,sd=25))
+polyplot2(Scores)
+```
+
+By default, the function labels all of the points and provides summary statistics in the margin. Generally speaking, each level/row provides a different category of measures of location and spread.
+
+- First/Top: Provides the mode of the distribution, with the sample size listed in the right margin
+- Second: Provides the quartiles (and median) of the distribution, with the interquartile range divided by 2 in the right margin
+- Third: Provides the means of the halves (and the whole) of the distribution, with the mean absolute deviation from the median in the right margin
+- Fourth: Provides the mean of the distribution and points +/- one standard deviation from the mean, with the standard deviation in the right margin
+- Fifth/Bottom: Provides the range (and midrange) of the distribution, with the range divided by 2 in the right margin
+
+### Using the PolyPlot to Determine Shape
+
+The following code demonstrates some of the available options for customizing the PolyPlot.Similarly, it demonstrates how the PolyPlot does a good job of approximating the shape of the underlying distribution.
+
+```{r}
+par(mfrow=c(1,2))
+polyplot2(Scores,histogram=TRUE,curve=FALSE,values=FALSE,main="PolyPlot2 plus Histogram",col="darkblue",bg="darkgoldenrod")
+polyplot2(Scores,histogram=FALSE,curve=TRUE,values=FALSE,main="PolyPlot2 plus Density Curve",col="darkblue",bg="darkgoldenrod")
+```
+
+Further explanation of the polyplot and how it can be used to understand the shape of the distribution is available in Seier and Bonett (2011).