An estimate that is slightly biased but robust, model independent, easy to compute, and easy to interpret, is better than one that is a non-biased, difficult to compute, mysterious, or not robust. That’s one of the differences between data science and statistics. Also, many times, reinventing the wheel can be more efficient than researching the literature for days, to perhaps find and old solution, barely documented, that won’t work any better than your (quickly designed) reinvented algorithm, on real data.
Starred articles were potential candidates for our picture of the week published in our weekly digest. Enjoy our new selection of articles and resources (R, data science, Python, machine learning etc.) Comments are from Vincent Granville.