10 Phrases That Kill Big Data Projects
1. “We Tried That. It Doesn’t Work.”
2. “Digital Is Really for the Younger Generation”
3. “Ideas Are Easy. Execution Is Hard.”
4. “Even Google Canceled Its “20 Percent” Time.”
5. “Only Silicon Valley Startups Do That.”
6. “You Need Experience First.”
7. “Corporate Won’t Like It.”
8. “We’re Not In That Business.”
9. “We’ll Put That on the List for Next Time.”
10. “Fast Follower Has Proven Best.”
A Hierarchical Bayesian Drive-Survival Model of the NFL
In this post, I describe a model of the football drive as a piecewise exponential competing risks survival model. I then fit an example implementation, embedding the drive model within a Hierarchical Bayesian model of the NFL.
Big Data: Driving Retail Strategy For The Future
So how does Big Data impact a retailer’s omnichannel strategy? Big data is driving the need for retailers to design their strategies across three key pillars: know better, align better and respond better.
• Know better (mind)
• Align better (soul)
• Respond better (heart)
Shiny for Interactive Application Development using R
This is a slidify-based deck used in my presentation to the Inland Northwest R user Group this past Friday (January 30, 2015). It introduces the shiny package from R-Studio and walks the group through the development of an interactive application that presents users with options to subset the iris dataset, generate a summary of the resulting dataset, and determine variables for a scatter plot and a box plot.
“Top 5 R Functions”
In preparation for a R Workgroup meeting, I started thinking about what would be my “Top 5 R Functions”. I ruled out the functions for basic mechanics – save, load, mean, etc. – they’re obviously critical, but every programming language has them, so there’s nothing especially “R” about them. I also ruled out the fancy statistical analysis functions like (g)lmer — most people (including me) start using R because they want to run those analyses so it seemed a little redundant. I started using R because I wanted to do growth curve analysis, so it seems like a weak endorsement to say that I like R because it can do growth curve analysis. No, I like R because it makes (many) somewhat complex data operations really, really easy. Understanding how take advantage of these R functions is what transformed my view of R from purely functional (I need to do analysis X and R has functions for doing analysis X) to an all-purpose tool that allows me to do data processing, management, analysis, and visualization extremely quickly and easily.
Embedding R-generated Interactive HTML pages in MS PowerPoint
Usually when I create slide decks these days I used markdown and slidy. However, I recently was asked to present using an existing Revolution Microsoft PowerPoint template. Trouble is, I’ve been spoilt with the advantages of using a HTML-based presentation technology and I wanted to include some interactive web elements. In particular, I wanted to use a motion chart generated with the fantastic googleVis package. Of course, that presented an issue – how was I to include some interactive HTML elements in my PowerPoint deck? The answer turned out to involve a PowerPoint plug-in called LiveWeb. These were the steps I took: …