Skip to main content
Engineering LibreTexts

1.2: A Word Of Warning

  • Page ID
    39258
  • \( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \) \( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)\(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\) \(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\)\(\newcommand{\AA}{\unicode[.8,0]{x212B}}\)

    Before we dive into the nitty gritty, let me leave you with one more general thought. It’s actually an application of something Spiderman once said: “with great power comes great responsibility.”

    Here’s the deal. The skills you’ll learn in this book are so powerful and (still!) so rare, that when you demonstrate them, people will think you can walk on water. If you continue in the discipline, you’ll become highly sought-after (and well paid). People will constantly be asking you to work with new data, to produce plots, predictions, and insights, and basically to do your magic. You’ll be treated as a guru: the oracle people go to when they want the scoop.

    This is ultra-cool, but also dangerous. Why dangerous? One simple reason: because when you make a data-related claim, people will believe you. Pretty much unquestioningly. Most of your colleagues won’t have the expertise or understanding to double-check your snazzy results. And it wouldn’t occur to them to do that anyway – after all, you’re the wizard.

    The truth of the matter is that data science lives on the knife edge of uncertainty. With our crystal ball, we can make non-obvious assertions about the past or present and even predict the future, but as with all “knowledge,” we must always hold it tentatively. We may be 95% confident that men are paid more than women...but that’s only 95% confidence, not 100%. We may have reason to believe that raising the minimum wage in a city will decrease poverty by 3%...but there’s a 1 in 20 chance that it might decrease it by as much as 6%, or even increase it by 1%.

    The abiding principle is that you should always be forthright about the limits of your bold claims, the caveats behind your beautiful plots, and the level of likelihood that your hypotheses will turn out to be wrong. Admittedly, doing so will make you seem a little less magic. There are lots of talking heads on television who deliberately obscure the level of uncertainty in their analyses so that they seem more certain (and more impressive) than they really are. To be responsible data scientists, though, we’re going to do the Spiderman thing and be up front and transparent about exactly what we’ve found, and what we might be missing.

    Believe me, this will make you powerful enough!


    This page titled 1.2: A Word Of Warning is shared under a CC BY-SA 4.0 license and was authored, remixed, and/or curated by Stephen Davies (allthemath.org) via source content that was edited to the style and standards of the LibreTexts platform; a detailed edit history is available upon request.