Resampling Methods: Bootstrap vs jackknife

Resampling is a way to reuse data to generate new, hypothetical samples (called resamples) that are representative of an underlying population. It’s used when:
You don’t know the underlying distribution for the population,
Traditional formulas are difficult or impossible to apply,
As a substitute for traditional methods.
Two popular tools are the bootstrap and jackknife.

Read Full Story

Creating corporate colour palettes for ggplot2

@drsimonj here to share how I create and reuse corporate color palettes for ggplot2.
You’ve started work as a data scientist at “drsimonj Inc” (congratulations, by the way) and PR have asked that all your Figures use the corporate colours. They send you the image below (coincidentally the Metro UI colors on color-hex.

Read Full Story