As a scientist, I directly use statistics every day, analysing and reporting results of experiments, and reading and evaluating the research of others. As a regular person, I indirectly use statistics every day.
Some are statistics that I have gathered, consciously or unconsciously. (When is the bus due? How likely am I to catch it if I wait another 5 minutes?)
Some are statistics that I’ve been explicitly exposed to – in advertisements, media reports, or conversations with people I know. (Will dressing like this help me get the job? Will this candidate’s policies really improve the economy? Will this candidate really implement these policies? How bad is my lack of regular exercise for my long-term health?)
Responsible use of statistics is one of the greatest boons to modern science – from the development and evaluation of medical innovations (yay, Florence Nightingale!) to the examination of global climate (it’s changing).
Irresponsible use of statistics is an increasing threat. From frauds misusing the numbers to promote quack alternatives to medicine, to news outlets misrepresenting results for the sake of a headline, to politicians and industry executives lying with a veneer of scientific credibility.
Without (responsible) statistics, we would be at the mercy of our appallingly bias-laden intuitions. (Be honest, did you get the Monty Hall problem right when you first came across it?) Without a basic understanding of statistics, we are at the mercy of people who will distort the data to try to convince us of anything.
A tiny side-note here: despite the popular aphorism, it is not true that you can prove anything you want with statistics. You can claim anything you want. If your audience is ignorant enough you might get away with it. But only by lying and distorting. Statistics don’t lie to people; people lie to people (and often to themselves.) If you understand statistics – and I mean the basic concepts, not the fancy mathematical equations – then it is much harder for someone to lie to you with statistics.
Okay, I’d love to go on at greater length. But I have some data to analyze.
In celebration, here are some things to check out. Enjoy!
- R, the best way to do statistics. It’s free and it’s friendly. It’s used in beginners courses, and it’s used by professional statisticians. Give it a try. You know you want to!
- Ben Goldacre’s Bad Science blog and book, with loads of tips about what to look out for in popular portrayals of science and statistics. (That book would serve as a good introduction to statistical thinking, among other things.)
- Hans Rosling’s presentation of beautiful statistics (YouTube) – proving that stats don’t have to be boring and opaque.