Benford's Law Graphed in R

Using R to replicate Sara Silverstein's post at BusinessInsider.com

A first-year student near and dear to my heart at the Kellogg School of Management thought I would be interested in this Business Insider story by Sara Silverstein on Benford’s Law. After sitting through the requisite ad, I became engrossed in Ms. Silverstein’s talk about what that law theoretically is and how it can be applied in financial forensics.

I thought I would try duplicating the demonstration in R.¹ This gave me a chance to compare and contrast the generation of combined bar- and line-plots using base R and ggplot2. It also gave me an opportunity to learn how to post RMarkdown output to blogger.

Using base R

Define the Benford Law function using log base 10 and plot the predicted values.

benlaw <- function(d) log10(1 + 1 / d)
digits <- 1:9
baseBarplot <- barplot(benlaw(digits), names.arg = digits, xlab = "First Digit", 
                       ylim = c(0, .35))

Remarks:

• That was easy!

Forking, Cloning, and Pull Requests with Github Desktop

This is the best explanation I've found of how to collaborate on someone else's repository. Bonus! it's a video: