This is a demonstration of what has been pointed out by [Gelman and colleagues](http://andrewgelman.com/2010/12/13/the_truth_wears/) that when dealing with truly small effects, screening results by statistical significance will leade to large Type-M (magnitude) and Type-S (sign) errors.
Modelling of /aw/ F1
This is a brief tutorial on how to subsample groups from a data frame using dplyr.
Basic meteorological stats for South Philly during Hurricane Sandy.
Testing whether this will render html5 slides correctly.