22min
Do statistics lie or tell the truth? Like words, they can be used to do both. Sometimes they clash with our personal experiences, other times they confirm them, but we could all benefit from learning to interpret them properly to avoid being taken advantage of. What really matters, according to Tim Harford, is following the ten simple rules he outlines in his book, The Data Detective, to help us learn a new and useful way to interpret data.
read more
read less
Analysis and key concepts
01.
Numbers, just like words, can be used to tell lies or to tell the truth
02.
Identifying any feelings and isolating them to help objectively and rationally assess the available data
03.
Assessing personal experience to understand when to trust it, when not to, and how to incorporate it into our evaluation of data
04.
Avoid premature enumeration: before passing judgement, make sure you understand the values you are dealing with, to avoid making incorrect assumptions
05.
Taking a step back to better enjoy the view: perspective influences our perception of reality, so we need to understand the context of the data
06.
Behind the scenes: data collected but not published can provide a great deal of information
07.
Ask yourself if there is anyone missing: research must be based on a reliable sample that reflects the whole population
08.
Demanding transparency at all times: an algorithm is not always better than humans when it comes to representing data. Both big data and small data are required to paint the full picture
09.
Don’t take your data sources for granted: the credibility of this science is built on the courage of those who apply it
10.
Remember that misinformation can make things look more attractive: it’s easier to produce than gathering real facts, so the trap is very inviting
11.
Keeping an open mind helps to predict and overcome crises
12.
Quotes
13.
Take-home message
Statistics could prove anything, true or false, which is why many people say they don't trust them. Moreover, in 1954, a book called How to Lie with Statistics was published, in which the American journalist Darrell Huff provided a series of examples to demonstrate how the data we are presented can be untrue or distorted, in order to warn against certain tricks that are used, even on a commercial level. Numbers, however, represent an objective reality that we can and must trust, provided we know how to read them and what questions to ask before interpreting their meaning: to help with this, Tim Harford has compiled a list of ten rules that can help us make sense of statistics and use them to better understand the world we live in. The list is based on the following principles: search your feelings, ponder your personal experience, avoid premature enumeration, take a step back and enjoy the view, get the backstory, ask who is missing, demand transparency when the computer says no, don’t take statistical bedrock for granted, remember that misinformation can also be beautiful, and keep an open mind.
By applying these daily rules, we can develop a greater awareness of the information we come into contact with, learning to distinguish between which part of it is accurate and which is not, and begin to broaden our perspective to a more truthful, complete picture of any given situation.
You'll have 7 days free, and if you're not satisfied after 30 days, you can get your money back.
Many useful tips to:
The author
Tim Harford is an economist. He has worked for Shell and the World Bank; for many years he wrote articles for “The Undercover Economist”, a column in the Financial Times. He has also written articles for Esquire, Forbes, Wired, New York Magazine, The Guardian and other newspapers. Harford has spoken at several TED events, at PopTech, and at the Sydney Opera House, as well as appearing on many television and radio shows. Harford was a member of the Royal Economic Society from 2011 until 2017, and he is an honorary member of the Royal Statistical Society. His first book, The Undercover Economist, sold over 1.5 million copies worldwide, and was translated into 30 languages.
Edition
Publishing house:
Riverhead Books
Year:
2022
Pages:
336
ISBN:
978-0593084663