The Bayesian Reproducibility Project

The Reproducibility Project was finally published this week in Science, and an outpouring of media articles followed. Headlines included “More Than 50% Psychology Studies Are Questionable: Study”, “Scientists Replicated 100 Psychology Studies, and Fewer Than Half Got the Same Results”, and “More than half of psychology papers are not reproducible”.

DL4J (Deeplearning for Java) – Getting Started

ND4J, Canova & DL4J

“A 99% TVaR is generally a 99.6% VaR”

The IQUIT R video series

I’ve uploaded 20+ R tutorials to YouTube for a new undergraduate course in Ecology and Evolutionary Biology at CU developed by Andrew Martin and Brett Melbourne, which in jocular anticipation was named IQUIT: an introduction to quantitative inference and thinking.

embeding a subplot in ggplot via subview

I implemented a function, subview, in ggtree that make it easy to embed a subplot in ggplot. – See more at: http://…/#sthash.hiqqHrPe.dpuf

First steps in data science: author-aware sentiment analysis

Step 1: Find a problem to work on
Step 2: Close your knowledge gaps
Step 3: Get your hands dirty
Step 4: Publish your results
Step 5: Improve results or move on

Evaluating recommender systems

Validation for recommender system might be tricky. There are a few things to consider, including formulation of the task, form of available feedback, and a metric to optimize for. We address these issues and present an example. We approach recommendation as a ranking task, meaning that we’re mainly interested in a relatively few items that we consider most relevant and are going to show to the user. This is known as top-K recommendation.